crypto: inside-secure - add SafeXcel EIP197 crypto engine driver

Add support for Inside Secure SafeXcel EIP197 cryptographic engine,
which can be found on Marvell Armada 7k and 8k boards. This driver
currently implements: ecb(aes), cbc(aes), sha1, sha224, sha256 and
hmac(sah1) algorithms.

Two firmwares are needed for this engine to work. Their are mostly used
for more advanced operations than the ones supported (as of now), but we
still need them to pass the data to the internal cryptographic engine.
Signed-off-by: NAntoine Tenart <antoine.tenart@free-electrons.com>
Signed-off-by: NHerbert Xu <herbert@gondor.apana.org.au>

drivers/crypto/Kconfig

@@ -655,4 +655,21 @@ config CRYPTO_DEV_BCM_SPU
 
 source "drivers/crypto/stm32/Kconfig"
 
+config CRYPTO_DEV_SAFEXCEL
+	tristate "Inside Secure's SafeXcel cryptographic engine driver"
+	depends on HAS_DMA && OF
+	depends on (ARM64 && ARCH_MVEBU) || (COMPILE_TEST && 64BIT)
+	select CRYPTO_AES
+	select CRYPTO_BLKCIPHER
+	select CRYPTO_HASH
+	select CRYPTO_HMAC
+	select CRYPTO_SHA1
+	select CRYPTO_SHA256
+	select CRYPTO_SHA512
+	help
+	  This driver interfaces with the SafeXcel EIP-197 cryptographic engine
+	  designed by Inside Secure. Select this if you want to use CBC/ECB
+	  chain mode, AES cipher mode and SHA1/SHA224/SHA256/SHA512 hash
+	  algorithms.
+
 endif # CRYPTO_HW

drivers/crypto/Makefile

@@ -41,3 +41,4 @@ obj-$(CONFIG_CRYPTO_DEV_UX500) += ux500/
 obj-$(CONFIG_CRYPTO_DEV_VIRTIO) += virtio/
 obj-$(CONFIG_CRYPTO_DEV_VMX) += vmx/
 obj-$(CONFIG_CRYPTO_DEV_BCM_SPU) += bcm/
+obj-$(CONFIG_CRYPTO_DEV_SAFEXCEL) += inside-secure/

drivers/crypto/inside-secure/Makefile

+obj-$(CONFIG_CRYPTO_DEV_SAFEXCEL) += crypto_safexcel.o
+crypto_safexcel-objs := safexcel.o safexcel_ring.o safexcel_cipher.o safexcel_hash.o

drivers/crypto/inside-secure/safexcel.c

+/*
+ * Copyright (C) 2017 Marvell
+ *
+ * Antoine Tenart <antoine.tenart@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/clk.h>
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmapool.h>
+#include <linux/firmware.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <linux/of_irq.h>
+#include <linux/platform_device.h>
+#include <linux/workqueue.h>
+
+#include <crypto/internal/hash.h>
+#include <crypto/internal/skcipher.h>
+
+#include "safexcel.h"
+
+static u32 max_rings = EIP197_MAX_RINGS;
+module_param(max_rings, uint, 0644);
+MODULE_PARM_DESC(max_rings, "Maximum number of rings to use.");
+
+static void eip197_trc_cache_init(struct safexcel_crypto_priv *priv)
+{
+	u32 val, htable_offset;
+	int i;
+
+	/* Enable the record cache memory access */
+	val = readl(priv->base + EIP197_CS_RAM_CTRL);
+	val &= ~EIP197_TRC_ENABLE_MASK;
+	val |= EIP197_TRC_ENABLE_0;
+	writel(val, priv->base + EIP197_CS_RAM_CTRL);
+
+	/* Clear all ECC errors */
+	writel(0, priv->base + EIP197_TRC_ECCCTRL);
+
+	/*
+	 * Make sure the cache memory is accessible by taking record cache into
+	 * reset.
+	 */
+	val = readl(priv->base + EIP197_TRC_PARAMS);
+	val |= EIP197_TRC_PARAMS_SW_RESET;
+	val &= ~EIP197_TRC_PARAMS_DATA_ACCESS;
+	writel(val, priv->base + EIP197_TRC_PARAMS);
+
+	/* Clear all records */
+	for (i = 0; i < EIP197_CS_RC_MAX; i++) {
+		u32 val, offset = EIP197_CLASSIFICATION_RAMS + i * EIP197_CS_RC_SIZE;
+
+		writel(EIP197_CS_RC_NEXT(EIP197_RC_NULL) |
+		       EIP197_CS_RC_PREV(EIP197_RC_NULL),
+		       priv->base + offset);
+
+		val = EIP197_CS_RC_NEXT(i+1) | EIP197_CS_RC_PREV(i-1);
+		if (i == 0)
+			val |= EIP197_CS_RC_PREV(EIP197_RC_NULL);
+		else if (i == EIP197_CS_RC_MAX - 1)
+			val |= EIP197_CS_RC_NEXT(EIP197_RC_NULL);
+		writel(val, priv->base + offset + sizeof(u32));
+	}
+
+	/* Clear the hash table entries */
+	htable_offset = EIP197_CS_RC_MAX * EIP197_CS_RC_SIZE;
+	for (i = 0; i < 64; i++)
+		writel(GENMASK(29, 0),
+		       priv->base + EIP197_CLASSIFICATION_RAMS + htable_offset + i * sizeof(u32));
+
+	/* Disable the record cache memory access */
+	val = readl(priv->base + EIP197_CS_RAM_CTRL);
+	val &= ~EIP197_TRC_ENABLE_MASK;
+	writel(val, priv->base + EIP197_CS_RAM_CTRL);
+
+	/* Write head and tail pointers of the record free chain */
+	val = EIP197_TRC_FREECHAIN_HEAD_PTR(0) |
+	      EIP197_TRC_FREECHAIN_TAIL_PTR(EIP197_CS_RC_MAX - 1);
+	writel(val, priv->base + EIP197_TRC_FREECHAIN);
+
+	/* Configure the record cache #1 */
+	val = EIP197_TRC_PARAMS2_RC_SZ_SMALL(EIP197_CS_TRC_REC_WC) |
+	      EIP197_TRC_PARAMS2_HTABLE_PTR(EIP197_CS_RC_MAX);
+	writel(val, priv->base + EIP197_TRC_PARAMS2);
+
+	/* Configure the record cache #2 */
+	val = EIP197_TRC_PARAMS_RC_SZ_LARGE(EIP197_CS_TRC_LG_REC_WC) |
+	      EIP197_TRC_PARAMS_BLK_TIMER_SPEED(1) |
+	      EIP197_TRC_PARAMS_HTABLE_SZ(2);
+	writel(val, priv->base + EIP197_TRC_PARAMS);
+}
+
+static void eip197_write_firmware(struct safexcel_crypto_priv *priv,
+				  const struct firmware *fw, u32 ctrl,
+				  u32 prog_en)
+{
+	const u32 *data = (const u32 *)fw->data;
+	u32 val;
+	int i;
+
+	/* Reset the engine to make its program memory accessible */
+	writel(EIP197_PE_ICE_x_CTRL_SW_RESET |
+	       EIP197_PE_ICE_x_CTRL_CLR_ECC_CORR |
+	       EIP197_PE_ICE_x_CTRL_CLR_ECC_NON_CORR,
+	       priv->base + ctrl);
+
+	/* Enable access to the program memory */
+	writel(prog_en, priv->base + EIP197_PE_ICE_RAM_CTRL);
+
+	/* Write the firmware */
+	for (i = 0; i < fw->size / sizeof(u32); i++)
+		writel(be32_to_cpu(data[i]),
+		       priv->base + EIP197_CLASSIFICATION_RAMS + i * sizeof(u32));
+
+	/* Disable access to the program memory */
+	writel(0, priv->base + EIP197_PE_ICE_RAM_CTRL);
+
+	/* Release engine from reset */
+	val = readl(priv->base + ctrl);
+	val &= ~EIP197_PE_ICE_x_CTRL_SW_RESET;
+	writel(val, priv->base + ctrl);
+}
+
+static int eip197_load_firmwares(struct safexcel_crypto_priv *priv)
+{
+	const char *fw_name[] = {"ifpp.bin", "ipue.bin"};
+	const struct firmware *fw[FW_NB];
+	int i, j, ret = 0;
+	u32 val;
+
+	for (i = 0; i < FW_NB; i++) {
+		ret = request_firmware(&fw[i], fw_name[i], priv->dev);
+		if (ret) {
+			dev_err(priv->dev,
+				"Failed to request firmware %s (%d)\n",
+				fw_name[i], ret);
+			goto release_fw;
+		}
+	 }
+
+	/* Clear the scratchpad memory */
+	val = readl(priv->base + EIP197_PE_ICE_SCRATCH_CTRL);
+	val |= EIP197_PE_ICE_SCRATCH_CTRL_CHANGE_TIMER |
+	       EIP197_PE_ICE_SCRATCH_CTRL_TIMER_EN |
+	       EIP197_PE_ICE_SCRATCH_CTRL_SCRATCH_ACCESS |
+	       EIP197_PE_ICE_SCRATCH_CTRL_CHANGE_ACCESS;
+	writel(val, priv->base + EIP197_PE_ICE_SCRATCH_CTRL);
+
+	memset(priv->base + EIP197_PE_ICE_SCRATCH_RAM, 0,
+	       EIP197_NUM_OF_SCRATCH_BLOCKS * sizeof(u32));
+
+	eip197_write_firmware(priv, fw[FW_IFPP], EIP197_PE_ICE_FPP_CTRL,
+			      EIP197_PE_ICE_RAM_CTRL_FPP_PROG_EN);
+
+	eip197_write_firmware(priv, fw[FW_IPUE], EIP197_PE_ICE_PUE_CTRL,
+			      EIP197_PE_ICE_RAM_CTRL_PUE_PROG_EN);
+
+release_fw:
+	for (j = 0; j < i; j++)
+		release_firmware(fw[j]);
+
+	return ret;
+}
+
+static int safexcel_hw_setup_cdesc_rings(struct safexcel_crypto_priv *priv)
+{
+	u32 hdw, cd_size_rnd, val;
+	int i;
+
+	hdw = readl(priv->base + EIP197_HIA_OPTIONS);
+	hdw &= GENMASK(27, 25);
+	hdw >>= 25;
+
+	cd_size_rnd = (priv->config.cd_size + (BIT(hdw) - 1)) >> hdw;
+
+	for (i = 0; i < priv->config.rings; i++) {
+		/* ring base address */
+		writel(lower_32_bits(priv->ring[i].cdr.base_dma),
+		       priv->base + EIP197_HIA_CDR(i) + EIP197_HIA_xDR_RING_BASE_ADDR_LO);
+		writel(upper_32_bits(priv->ring[i].cdr.base_dma),
+		       priv->base + EIP197_HIA_CDR(i) + EIP197_HIA_xDR_RING_BASE_ADDR_HI);
+
+		writel(EIP197_xDR_DESC_MODE_64BIT | (priv->config.cd_offset << 16) |
+		       priv->config.cd_size,
+		       priv->base + EIP197_HIA_CDR(i) + EIP197_HIA_xDR_DESC_SIZE);
+		writel(((EIP197_FETCH_COUNT * (cd_size_rnd << hdw)) << 16) |
+		       (EIP197_FETCH_COUNT * priv->config.cd_offset),
+		       priv->base + EIP197_HIA_CDR(i) + EIP197_HIA_xDR_CFG);
+
+		/* Configure DMA tx control */
+		val = EIP197_HIA_xDR_CFG_WR_CACHE(WR_CACHE_3BITS);
+		val |= EIP197_HIA_xDR_CFG_RD_CACHE(RD_CACHE_3BITS);
+		writel(val,
+		       priv->base + EIP197_HIA_CDR(i) + EIP197_HIA_xDR_DMA_CFG);
+
+		/* clear any pending interrupt */
+		writel(GENMASK(5, 0),
+		       priv->base + EIP197_HIA_CDR(i) + EIP197_HIA_xDR_STAT);
+	}
+
+	return 0;
+}
+
+static int safexcel_hw_setup_rdesc_rings(struct safexcel_crypto_priv *priv)
+{
+	u32 hdw, rd_size_rnd, val;
+	int i;
+
+	hdw = readl(priv->base + EIP197_HIA_OPTIONS);
+	hdw &= GENMASK(27, 25);
+	hdw >>= 25;
+
+	rd_size_rnd = (priv->config.rd_size + (BIT(hdw) - 1)) >> hdw;
+
+	for (i = 0; i < priv->config.rings; i++) {
+		/* ring base address */
+		writel(lower_32_bits(priv->ring[i].rdr.base_dma),
+		       priv->base + EIP197_HIA_RDR(i) + EIP197_HIA_xDR_RING_BASE_ADDR_LO);
+		writel(upper_32_bits(priv->ring[i].rdr.base_dma),
+		       priv->base + EIP197_HIA_RDR(i) + EIP197_HIA_xDR_RING_BASE_ADDR_HI);
+
+		writel(EIP197_xDR_DESC_MODE_64BIT | (priv->config.rd_offset << 16) |
+		       priv->config.rd_size,
+		       priv->base + EIP197_HIA_RDR(i) + EIP197_HIA_xDR_DESC_SIZE);
+
+		writel(((EIP197_FETCH_COUNT * (rd_size_rnd << hdw)) << 16) |
+		       (EIP197_FETCH_COUNT * priv->config.rd_offset),
+		       priv->base + EIP197_HIA_RDR(i) + EIP197_HIA_xDR_CFG);
+
+		/* Configure DMA tx control */
+		val = EIP197_HIA_xDR_CFG_WR_CACHE(WR_CACHE_3BITS);
+		val |= EIP197_HIA_xDR_CFG_RD_CACHE(RD_CACHE_3BITS);
+		val |= EIP197_HIA_xDR_WR_RES_BUF | EIP197_HIA_xDR_WR_CTRL_BUG;
+		writel(val,
+		       priv->base + EIP197_HIA_RDR(i) + EIP197_HIA_xDR_DMA_CFG);
+
+		/* clear any pending interrupt */
+		writel(GENMASK(7, 0),
+		       priv->base + EIP197_HIA_RDR(i) + EIP197_HIA_xDR_STAT);
+
+		/* enable ring interrupt */
+		val = readl(priv->base + EIP197_HIA_AIC_R_ENABLE_CTRL(i));
+		val |= EIP197_RDR_IRQ(i);
+		writel(val, priv->base + EIP197_HIA_AIC_R_ENABLE_CTRL(i));
+	}
+
+	return 0;
+}
+
+static int safexcel_hw_init(struct safexcel_crypto_priv *priv)
+{
+	u32 version, val;
+	int i, ret;
+
+	/* Determine endianess and configure byte swap */
+	version = readl(priv->base + EIP197_HIA_VERSION);
+	val = readl(priv->base + EIP197_HIA_MST_CTRL);
+
+	if ((version & 0xffff) == EIP197_HIA_VERSION_BE)
+		val |= EIP197_MST_CTRL_BYTE_SWAP;
+	else if (((version >> 16) & 0xffff) == EIP197_HIA_VERSION_LE)
+		val |= (EIP197_MST_CTRL_NO_BYTE_SWAP >> 24);
+
+	writel(val, priv->base + EIP197_HIA_MST_CTRL);
+
+
+	/* Configure wr/rd cache values */
+	writel(EIP197_MST_CTRL_RD_CACHE(RD_CACHE_4BITS) |
+	       EIP197_MST_CTRL_WD_CACHE(WR_CACHE_4BITS),
+	       priv->base + EIP197_MST_CTRL);
+
+	/* Interrupts reset */
+
+	/* Disable all global interrupts */
+	writel(0, priv->base + EIP197_HIA_AIC_G_ENABLE_CTRL);
+
+	/* Clear any pending interrupt */
+	writel(GENMASK(31, 0), priv->base + EIP197_HIA_AIC_G_ACK);
+
+	/* Data Fetch Engine configuration */
+
+	/* Reset all DFE threads */
+	writel(EIP197_DxE_THR_CTRL_RESET_PE,
+	       priv->base + EIP197_HIA_DFE_THR_CTRL);
+
+	/* Reset HIA input interface arbiter */
+	writel(EIP197_HIA_RA_PE_CTRL_RESET,
+	       priv->base + EIP197_HIA_RA_PE_CTRL);
+
+	/* DMA transfer size to use */
+	val = EIP197_HIA_DFE_CFG_DIS_DEBUG;
+	val |= EIP197_HIA_DxE_CFG_MIN_DATA_SIZE(5) | EIP197_HIA_DxE_CFG_MAX_DATA_SIZE(9);
+	val |= EIP197_HIA_DxE_CFG_MIN_CTRL_SIZE(5) | EIP197_HIA_DxE_CFG_MAX_CTRL_SIZE(7);
+	val |= EIP197_HIA_DxE_CFG_DATA_CACHE_CTRL(RD_CACHE_3BITS);
+	val |= EIP197_HIA_DxE_CFG_CTRL_CACHE_CTRL(RD_CACHE_3BITS);
+	writel(val, priv->base + EIP197_HIA_DFE_CFG);
+
+	/* Leave the DFE threads reset state */
+	writel(0, priv->base + EIP197_HIA_DFE_THR_CTRL);
+
+	/* Configure the procesing engine thresholds */
+	writel(EIP197_PE_IN_xBUF_THRES_MIN(5) | EIP197_PE_IN_xBUF_THRES_MAX(9),
+	      priv->base + EIP197_PE_IN_DBUF_THRES);
+	writel(EIP197_PE_IN_xBUF_THRES_MIN(5) | EIP197_PE_IN_xBUF_THRES_MAX(7),
+	      priv->base + EIP197_PE_IN_TBUF_THRES);
+
+	/* enable HIA input interface arbiter and rings */
+	writel(EIP197_HIA_RA_PE_CTRL_EN | GENMASK(priv->config.rings - 1, 0),
+	       priv->base + EIP197_HIA_RA_PE_CTRL);
+
+	/* Data Store Engine configuration */
+
+	/* Reset all DSE threads */
+	writel(EIP197_DxE_THR_CTRL_RESET_PE,
+	       priv->base + EIP197_HIA_DSE_THR_CTRL);
+
+	/* Wait for all DSE threads to complete */
+	while ((readl(priv->base + EIP197_HIA_DSE_THR_STAT) &
+		GENMASK(15, 12)) != GENMASK(15, 12))
+		;
+
+	/* DMA transfer size to use */
+	val = EIP197_HIA_DSE_CFG_DIS_DEBUG;
+	val |= EIP197_HIA_DxE_CFG_MIN_DATA_SIZE(7) | EIP197_HIA_DxE_CFG_MAX_DATA_SIZE(8);
+	val |= EIP197_HIA_DxE_CFG_DATA_CACHE_CTRL(RD_CACHE_3BITS);
+	writel(val, priv->base + EIP197_HIA_DSE_CFG);
+
+	/* Leave the DSE threads reset state */
+	writel(0, priv->base + EIP197_HIA_DSE_THR_CTRL);
+
+	/* Configure the procesing engine thresholds */
+	writel(EIP197_PE_OUT_DBUF_THRES_MIN(7) | EIP197_PE_OUT_DBUF_THRES_MAX(8),
+	       priv->base + EIP197_PE_OUT_DBUF_THRES);
+
+	/* Processing Engine configuration */
+
+	/* H/W capabilities selection */
+	val = EIP197_FUNCTION_RSVD;
+	val |= EIP197_PROTOCOL_ENCRYPT_ONLY | EIP197_PROTOCOL_HASH_ONLY;
+	val |= EIP197_ALG_AES_ECB | EIP197_ALG_AES_CBC;
+	val |= EIP197_ALG_SHA1 | EIP197_ALG_HMAC_SHA1;
+	val |= EIP197_ALG_SHA2;
+	writel(val, priv->base + EIP197_PE_EIP96_FUNCTION_EN);
+
+	/* Command Descriptor Rings prepare */
+	for (i = 0; i < priv->config.rings; i++) {
+		/* Clear interrupts for this ring */
+		writel(GENMASK(31, 0),
+		       priv->base + EIP197_HIA_AIC_R_ENABLE_CLR(i));
+
+		/* Disable external triggering */
+		writel(0, priv->base + EIP197_HIA_CDR(i) + EIP197_HIA_xDR_CFG);
+
+		/* Clear the pending prepared counter */
+		writel(EIP197_xDR_PREP_CLR_COUNT,
+		       priv->base + EIP197_HIA_CDR(i) + EIP197_HIA_xDR_PREP_COUNT);
+
+		/* Clear the pending processed counter */
+		writel(EIP197_xDR_PROC_CLR_COUNT,
+		       priv->base + EIP197_HIA_CDR(i) + EIP197_HIA_xDR_PROC_COUNT);
+
+		writel(0,
+		       priv->base + EIP197_HIA_CDR(i) + EIP197_HIA_xDR_PREP_PNTR);
+		writel(0,
+		       priv->base + EIP197_HIA_CDR(i) + EIP197_HIA_xDR_PROC_PNTR);
+
+		writel((EIP197_DEFAULT_RING_SIZE * priv->config.cd_offset) << 2,
+		       priv->base + EIP197_HIA_CDR(i) + EIP197_HIA_xDR_RING_SIZE);
+	}
+
+	/* Result Descriptor Ring prepare */
+	for (i = 0; i < priv->config.rings; i++) {
+		/* Disable external triggering*/
+		writel(0, priv->base + EIP197_HIA_RDR(i) + EIP197_HIA_xDR_CFG);
+
+		/* Clear the pending prepared counter */
+		writel(EIP197_xDR_PREP_CLR_COUNT,
+		       priv->base + EIP197_HIA_RDR(i) + EIP197_HIA_xDR_PREP_COUNT);
+
+		/* Clear the pending processed counter */
+		writel(EIP197_xDR_PROC_CLR_COUNT,
+		       priv->base + EIP197_HIA_RDR(i) + EIP197_HIA_xDR_PROC_COUNT);
+
+		writel(0,
+		       priv->base + EIP197_HIA_RDR(i) + EIP197_HIA_xDR_PREP_PNTR);
+		writel(0,
+		       priv->base + EIP197_HIA_RDR(i) + EIP197_HIA_xDR_PROC_PNTR);
+
+		/* Ring size */
+		writel((EIP197_DEFAULT_RING_SIZE * priv->config.rd_offset) << 2,
+		       priv->base + EIP197_HIA_RDR(i) + EIP197_HIA_xDR_RING_SIZE);
+	}
+
+	/* Enable command descriptor rings */
+	writel(EIP197_DxE_THR_CTRL_EN | GENMASK(priv->config.rings - 1, 0),
+	       priv->base + EIP197_HIA_DFE_THR_CTRL);
+
+	/* Enable result descriptor rings */
+	writel(EIP197_DxE_THR_CTRL_EN | GENMASK(priv->config.rings - 1, 0),
+	       priv->base + EIP197_HIA_DSE_THR_CTRL);
+
+	/* Clear any HIA interrupt */
+	writel(GENMASK(30, 20), priv->base + EIP197_HIA_AIC_G_ACK);
+
+	eip197_trc_cache_init(priv);
+
+	ret = eip197_load_firmwares(priv);
+	if (ret)
+		return ret;
+
+	safexcel_hw_setup_cdesc_rings(priv);
+	safexcel_hw_setup_rdesc_rings(priv);
+
+	return 0;
+}
+
+void safexcel_dequeue(struct safexcel_crypto_priv *priv)
+{
+	struct crypto_async_request *req, *backlog;
+	struct safexcel_context *ctx;
+	struct safexcel_request *request;
+	int i, ret, n = 0, nreq[EIP197_MAX_RINGS] = {0};
+	int cdesc[EIP197_MAX_RINGS] = {0}, rdesc[EIP197_MAX_RINGS] = {0};
+	int commands, results;
+
+	do {
+		spin_lock_bh(&priv->lock);
+		req = crypto_dequeue_request(&priv->queue);
+		backlog = crypto_get_backlog(&priv->queue);
+		spin_unlock_bh(&priv->lock);
+
+		if (!req)
+			goto finalize;
+
+		request = kzalloc(sizeof(*request), EIP197_GFP_FLAGS(*req));
+		if (!request)
+			goto requeue;
+
+		ctx = crypto_tfm_ctx(req->tfm);
+		ret = ctx->send(req, ctx->ring, request, &commands, &results);
+		if (ret) {
+			kfree(request);
+requeue:
+			spin_lock_bh(&priv->lock);
+			crypto_enqueue_request(&priv->queue, req);
+			spin_unlock_bh(&priv->lock);
+
+			priv->need_dequeue = true;
+			continue;
+		}
+
+		if (backlog)
+			backlog->complete(backlog, -EINPROGRESS);
+
+		spin_lock_bh(&priv->ring[ctx->ring].egress_lock);
+		list_add_tail(&request->list, &priv->ring[ctx->ring].list);
+		spin_unlock_bh(&priv->ring[ctx->ring].egress_lock);
+
+		cdesc[ctx->ring] += commands;
+		rdesc[ctx->ring] += results;
+
+		nreq[ctx->ring]++;
+	} while (n++ < EIP197_MAX_BATCH_SZ);
+
+finalize:
+	if (n == EIP197_MAX_BATCH_SZ)
+		priv->need_dequeue = true;
+	else if (!n)
+		return;
+
+	for (i = 0; i < priv->config.rings; i++) {
+		if (!nreq[i])
+			continue;
+
+		spin_lock_bh(&priv->ring[i].lock);
+
+		/* Configure when we want an interrupt */
+		writel(EIP197_HIA_RDR_THRESH_PKT_MODE |
+		       EIP197_HIA_RDR_THRESH_PROC_PKT(nreq[i]),
+		       priv->base + EIP197_HIA_RDR(i) + EIP197_HIA_xDR_THRESH);
+
+		/* let the RDR know we have pending descriptors */
+		writel((rdesc[i] * priv->config.rd_offset) << 2,
+		       priv->base + EIP197_HIA_RDR(i) + EIP197_HIA_xDR_PREP_COUNT);
+
+		/* let the CDR know we have pending descriptors */
+		writel((cdesc[i] * priv->config.cd_offset) << 2,
+		       priv->base + EIP197_HIA_CDR(i) + EIP197_HIA_xDR_PREP_COUNT);
+
+		spin_unlock_bh(&priv->ring[i].lock);
+	}
+}
+
+void safexcel_free_context(struct safexcel_crypto_priv *priv,
+			   struct crypto_async_request *req,
+			   int result_sz)
+{
+	struct safexcel_context *ctx = crypto_tfm_ctx(req->tfm);
+
+	if (ctx->result_dma)
+		dma_unmap_single(priv->dev, ctx->result_dma, result_sz,
+				 DMA_FROM_DEVICE);
+
+	if (ctx->cache) {
+		dma_unmap_single(priv->dev, ctx->cache_dma, ctx->cache_sz,
+				 DMA_TO_DEVICE);
+		kfree(ctx->cache);
+		ctx->cache = NULL;
+		ctx->cache_sz = 0;
+	}
+}
+
+void safexcel_complete(struct safexcel_crypto_priv *priv, int ring)
+{
+	struct safexcel_command_desc *cdesc;
+
+	/* Acknowledge the command descriptors */
+	do {
+		cdesc = safexcel_ring_next_rptr(priv, &priv->ring[ring].cdr);
+		if (IS_ERR(cdesc)) {
+			dev_err(priv->dev,
+				"Could not retrieve the command descriptor\n");
+			return;
+		}
+	} while (!cdesc->last_seg);
+}
+
+void safexcel_inv_complete(struct crypto_async_request *req, int error)
+{
+	struct safexcel_inv_result *result = req->data;
+
+	if (error == -EINPROGRESS)
+		return;
+
+	result->error = error;
+	complete(&result->completion);
+}
+
+int safexcel_invalidate_cache(struct crypto_async_request *async,
+			      struct safexcel_context *ctx,
+			      struct safexcel_crypto_priv *priv,
+			      dma_addr_t ctxr_dma, int ring,
+			      struct safexcel_request *request)
+{
+	struct safexcel_command_desc *cdesc;
+	struct safexcel_result_desc *rdesc;
+	int ret = 0;
+
+	spin_lock_bh(&priv->ring[ring].egress_lock);
+
+	/* Prepare command descriptor */
+	cdesc = safexcel_add_cdesc(priv, ring, true, true, 0, 0, 0, ctxr_dma);
+	if (IS_ERR(cdesc)) {
+		ret = PTR_ERR(cdesc);
+		goto unlock;
+	}
+
+	cdesc->control_data.type = EIP197_TYPE_EXTENDED;
+	cdesc->control_data.options = 0;
+	cdesc->control_data.refresh = 0;
+	cdesc->control_data.control0 = CONTEXT_CONTROL_INV_TR;
+
+	/* Prepare result descriptor */
+	rdesc = safexcel_add_rdesc(priv, ring, true, true, 0, 0);
+
+	if (IS_ERR(rdesc)) {
+		ret = PTR_ERR(rdesc);
+		goto cdesc_rollback;
+	}
+
+	request->req = async;
+	goto unlock;
+
+cdesc_rollback:
+	safexcel_ring_rollback_wptr(priv, &priv->ring[ring].cdr);
+
+unlock:
+	spin_unlock_bh(&priv->ring[ring].egress_lock);
+	return ret;
+}
+
+static inline void safexcel_handle_result_descriptor(struct safexcel_crypto_priv *priv,
+						     int ring)
+{
+	struct safexcel_request *sreq;
+	struct safexcel_context *ctx;
+	int ret, i, nreq, ndesc = 0;
+	bool should_complete;
+
+	nreq = readl(priv->base + EIP197_HIA_RDR(ring) + EIP197_HIA_xDR_PROC_COUNT);
+	nreq >>= 24;
+	nreq &= GENMASK(6, 0);
+	if (!nreq)
+		return;
+
+	for (i = 0; i < nreq; i++) {
+		spin_lock_bh(&priv->ring[ring].egress_lock);
+		sreq = list_first_entry(&priv->ring[ring].list,
+					struct safexcel_request, list);
+		list_del(&sreq->list);
+		spin_unlock_bh(&priv->ring[ring].egress_lock);
+
+		ctx = crypto_tfm_ctx(sreq->req->tfm);
+		ndesc = ctx->handle_result(priv, ring, sreq->req,
+					   &should_complete, &ret);
+		if (ndesc < 0) {
+			dev_err(priv->dev, "failed to handle result (%d)", ndesc);
+			return;
+		}
+
+		writel(EIP197_xDR_PROC_xD_PKT(1) |
+		       EIP197_xDR_PROC_xD_COUNT(ndesc * priv->config.rd_offset),
+		       priv->base + EIP197_HIA_RDR(ring) + EIP197_HIA_xDR_PROC_COUNT);
+
+		if (should_complete) {
+			local_bh_disable();
+			sreq->req->complete(sreq->req, ret);
+			local_bh_enable();
+		}
+
+		kfree(sreq);
+	}
+}
+
+static void safexcel_handle_result_work(struct work_struct *work)
+{
+	struct safexcel_work_data *data =
+			container_of(work, struct safexcel_work_data, work);
+	struct safexcel_crypto_priv *priv = data->priv;
+
+	safexcel_handle_result_descriptor(priv, data->ring);
+
+	if (priv->need_dequeue) {
+		priv->need_dequeue = false;
+		safexcel_dequeue(data->priv);
+	}
+}
+
+struct safexcel_ring_irq_data {
+	struct safexcel_crypto_priv *priv;
+	int ring;
+};
+
+static irqreturn_t safexcel_irq_ring(int irq, void *data)
+{
+	struct safexcel_ring_irq_data *irq_data = data;
+	struct safexcel_crypto_priv *priv = irq_data->priv;
+	int ring = irq_data->ring;
+	u32 status, stat;
+
+	status = readl(priv->base + EIP197_HIA_AIC_R_ENABLED_STAT(ring));
+	if (!status)
+		return IRQ_NONE;
+
+	/* RDR interrupts */
+	if (status & EIP197_RDR_IRQ(ring)) {
+		stat = readl(priv->base + EIP197_HIA_RDR(ring) + EIP197_HIA_xDR_STAT);
+
+		if (unlikely(stat & EIP197_xDR_ERR)) {
+			/*
+			 * Fatal error, the RDR is unusable and must be
+			 * reinitialized. This should not happen under
+			 * normal circumstances.
+			 */
+			dev_err(priv->dev, "RDR: fatal error.");
+		} else if (likely(stat & EIP197_xDR_THRESH)) {
+			queue_work(priv->ring[ring].workqueue, &priv->ring[ring].work_data.work);
+		}
+
+		/* ACK the interrupts */
+		writel(stat & 0xff,
+		       priv->base + EIP197_HIA_RDR(ring) + EIP197_HIA_xDR_STAT);
+	}
+
+	/* ACK the interrupts */
+	writel(status, priv->base + EIP197_HIA_AIC_R_ACK(ring));
+
+	return IRQ_HANDLED;
+}
+
+static int safexcel_request_ring_irq(struct platform_device *pdev, const char *name,
+				     irq_handler_t handler,
+				     struct safexcel_ring_irq_data *ring_irq_priv)
+{
+	int ret, irq = platform_get_irq_byname(pdev, name);
+
+	if (irq < 0) {
+		dev_err(&pdev->dev, "unable to get IRQ '%s'\n", name);
+		return irq;
+	}
+
+	ret = devm_request_irq(&pdev->dev, irq, handler, 0,
+			       dev_name(&pdev->dev), ring_irq_priv);
+	if (ret) {
+		dev_err(&pdev->dev, "unable to request IRQ %d\n", irq);
+		return ret;
+	}
+
+	return irq;
+}
+
+static struct safexcel_alg_template *safexcel_algs[] = {
+	&safexcel_alg_ecb_aes,
+	&safexcel_alg_cbc_aes,
+	&safexcel_alg_sha1,
+	&safexcel_alg_sha224,
+	&safexcel_alg_sha256,
+	&safexcel_alg_hmac_sha1,
+};
+
+static int safexcel_register_algorithms(struct safexcel_crypto_priv *priv)
+{
+	int i, j, ret = 0;
+
+	for (i = 0; i < ARRAY_SIZE(safexcel_algs); i++) {
+		safexcel_algs[i]->priv = priv;
+
+		if (safexcel_algs[i]->type == SAFEXCEL_ALG_TYPE_SKCIPHER)
+			ret = crypto_register_skcipher(&safexcel_algs[i]->alg.skcipher);
+		else
+			ret = crypto_register_ahash(&safexcel_algs[i]->alg.ahash);
+
+		if (ret)
+			goto fail;
+	}
+
+	return 0;
+
+fail:
+	for (j = 0; j < i; j++) {
+		if (safexcel_algs[j]->type == SAFEXCEL_ALG_TYPE_SKCIPHER)
+			crypto_unregister_skcipher(&safexcel_algs[j]->alg.skcipher);
+		else
+			crypto_unregister_ahash(&safexcel_algs[j]->alg.ahash);
+	}
+
+	return ret;
+}
+
+static void safexcel_unregister_algorithms(struct safexcel_crypto_priv *priv)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(safexcel_algs); i++) {
+		if (safexcel_algs[i]->type == SAFEXCEL_ALG_TYPE_SKCIPHER)
+			crypto_unregister_skcipher(&safexcel_algs[i]->alg.skcipher);
+		else
+			crypto_unregister_ahash(&safexcel_algs[i]->alg.ahash);
+	}
+}
+
+static void safexcel_configure(struct safexcel_crypto_priv *priv)
+{
+	u32 val, mask;
+
+	val = readl(priv->base + EIP197_HIA_OPTIONS);
+	val = (val & GENMASK(27, 25)) >> 25;
+	mask = BIT(val) - 1;
+
+	val = readl(priv->base + EIP197_HIA_OPTIONS);
+	priv->config.rings = min_t(u32, val & GENMASK(3, 0), max_rings);
+
+	priv->config.cd_size = (sizeof(struct safexcel_command_desc) / sizeof(u32));
+	priv->config.cd_offset = (priv->config.cd_size + mask) & ~mask;
+
+	priv->config.rd_size = (sizeof(struct safexcel_result_desc) / sizeof(u32));
+	priv->config.rd_offset = (priv->config.rd_size + mask) & ~mask;
+}
+
+static int safexcel_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct resource *res;
+	struct safexcel_crypto_priv *priv;
+	u64 dma_mask;
+	int i, ret;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->dev = dev;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	priv->base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(priv->base)) {
+		dev_err(dev, "failed to get resource\n");
+		return PTR_ERR(priv->base);
+	}
+
+	priv->clk = of_clk_get(dev->of_node, 0);
+	if (!IS_ERR(priv->clk)) {
+		ret = clk_prepare_enable(priv->clk);
+		if (ret) {
+			dev_err(dev, "unable to enable clk (%d)\n", ret);
+			return ret;
+		}
+	} else {
+		/* The clock isn't mandatory */
+		if (PTR_ERR(priv->clk) == -EPROBE_DEFER)
+			return -EPROBE_DEFER;
+	}
+
+	if (of_property_read_u64(dev->of_node, "dma-mask", &dma_mask))
+		dma_mask = DMA_BIT_MASK(64);
+	ret = dma_set_mask_and_coherent(dev, dma_mask);
+	if (ret)
+		goto err_clk;
+
+	priv->context_pool = dmam_pool_create("safexcel-context", dev,
+					      sizeof(struct safexcel_context_record),
+					      1, 0);
+	if (!priv->context_pool) {
+		ret = -ENOMEM;
+		goto err_clk;
+	}
+
+	safexcel_configure(priv);
+
+	for (i = 0; i < priv->config.rings; i++) {
+		char irq_name[6] = {0}; /* "ringX\0" */
+		char wq_name[9] = {0}; /* "wq_ringX\0" */
+		int irq;
+		struct safexcel_ring_irq_data *ring_irq;
+
+		ret = safexcel_init_ring_descriptors(priv,
+						     &priv->ring[i].cdr,
+						     &priv->ring[i].rdr);
+		if (ret)
+			goto err_clk;
+
+		ring_irq = devm_kzalloc(dev, sizeof(*ring_irq), GFP_KERNEL);
+		if (!ring_irq) {
+			ret = -ENOMEM;
+			goto err_clk;
+		}
+
+		ring_irq->priv = priv;
+		ring_irq->ring = i;
+
+		snprintf(irq_name, 6, "ring%d", i);
+		irq = safexcel_request_ring_irq(pdev, irq_name, safexcel_irq_ring,
+						ring_irq);
+
+		if (irq < 0)
+			goto err_clk;
+
+		priv->ring[i].work_data.priv = priv;
+		priv->ring[i].work_data.ring = i;
+		INIT_WORK(&priv->ring[i].work_data.work, safexcel_handle_result_work);
+
+		snprintf(wq_name, 9, "wq_ring%d", i);
+		priv->ring[i].workqueue = create_singlethread_workqueue(wq_name);
+		if (!priv->ring[i].workqueue) {
+			ret = -ENOMEM;
+			goto err_clk;
+		}
+
+		INIT_LIST_HEAD(&priv->ring[i].list);
+		spin_lock_init(&priv->ring[i].lock);
+		spin_lock_init(&priv->ring[i].egress_lock);
+	}
+
+	platform_set_drvdata(pdev, priv);
+	atomic_set(&priv->ring_used, 0);
+
+	spin_lock_init(&priv->lock);
+	crypto_init_queue(&priv->queue, EIP197_DEFAULT_RING_SIZE);
+
+	ret = safexcel_hw_init(priv);
+	if (ret) {
+		dev_err(dev, "EIP h/w init failed (%d)\n", ret);
+		goto err_clk;
+	}
+
+	ret = safexcel_register_algorithms(priv);
+	if (ret) {
+		dev_err(dev, "Failed to register algorithms (%d)\n", ret);
+		goto err_clk;
+	}
+
+	return 0;
+
+err_clk:
+	clk_disable_unprepare(priv->clk);
+	return ret;
+}
+
+
+static int safexcel_remove(struct platform_device *pdev)
+{
+	struct safexcel_crypto_priv *priv = platform_get_drvdata(pdev);
+	int i;
+
+	safexcel_unregister_algorithms(priv);
+	clk_disable_unprepare(priv->clk);
+
+	for (i = 0; i < priv->config.rings; i++)
+		destroy_workqueue(priv->ring[i].workqueue);
+
+	return 0;
+}
+
+static const struct of_device_id safexcel_of_match_table[] = {
+	{ .compatible = "inside-secure,safexcel-eip197" },
+	{},
+};
+
+
+static struct platform_driver  crypto_safexcel = {
+	.probe		= safexcel_probe,
+	.remove		= safexcel_remove,
+	.driver		= {
+		.name	= "crypto-safexcel",
+		.of_match_table = safexcel_of_match_table,
+	},
+};
+module_platform_driver(crypto_safexcel);
+
+MODULE_AUTHOR("Antoine Tenart <antoine.tenart@free-electrons.com>");
+MODULE_AUTHOR("Ofer Heifetz <oferh@marvell.com>");
+MODULE_AUTHOR("Igal Liberman <igall@marvell.com>");
+MODULE_DESCRIPTION("Support for SafeXcel cryptographic engine EIP197");
+MODULE_LICENSE("GPL v2");

drivers/crypto/inside-secure/safexcel.h

+/*
+ * Copyright (C) 2017 Marvell
+ *
+ * Antoine Tenart <antoine.tenart@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#ifndef __SAFEXCEL_H__
+#define __SAFEXCEL_H__
+
+#include <crypto/algapi.h>
+#include <crypto/internal/hash.h>
+#include <crypto/skcipher.h>
+
+#define EIP197_HIA_VERSION_LE			0xca35
+#define EIP197_HIA_VERSION_BE			0x35ca
+
+/* Static configuration */
+#define EIP197_DEFAULT_RING_SIZE		64
+#define EIP197_MAX_TOKENS			5
+#define EIP197_MAX_RINGS			4
+#define EIP197_FETCH_COUNT			1
+#define EIP197_MAX_BATCH_SZ			8
+
+#define EIP197_GFP_FLAGS(base)	((base).flags & CRYPTO_TFM_REQ_MAY_SLEEP ? \
+				 GFP_KERNEL : GFP_ATOMIC)
+
+/* CDR/RDR register offsets */
+#define EIP197_HIA_xDR_OFF(r)			(0x80000 + (r) * 0x1000)
+#define EIP197_HIA_CDR(r)			(EIP197_HIA_xDR_OFF(r))
+#define EIP197_HIA_RDR(r)			(EIP197_HIA_xDR_OFF(r) + 0x800)
+#define EIP197_HIA_xDR_RING_BASE_ADDR_LO	0x0
+#define EIP197_HIA_xDR_RING_BASE_ADDR_HI	0x4
+#define EIP197_HIA_xDR_RING_SIZE		0x18
+#define EIP197_HIA_xDR_DESC_SIZE		0x1c
+#define EIP197_HIA_xDR_CFG			0x20
+#define EIP197_HIA_xDR_DMA_CFG			0x24
+#define EIP197_HIA_xDR_THRESH			0x28
+#define EIP197_HIA_xDR_PREP_COUNT		0x2c
+#define EIP197_HIA_xDR_PROC_COUNT		0x30
+#define EIP197_HIA_xDR_PREP_PNTR		0x34
+#define EIP197_HIA_xDR_PROC_PNTR		0x38
+#define EIP197_HIA_xDR_STAT			0x3c
+
+/* register offsets */
+#define EIP197_HIA_DFE_CFG			0x8c000
+#define EIP197_HIA_DFE_THR_CTRL			0x8c040
+#define EIP197_HIA_DFE_THR_STAT			0x8c044
+#define EIP197_HIA_DSE_CFG			0x8d000
+#define EIP197_HIA_DSE_THR_CTRL			0x8d040
+#define EIP197_HIA_DSE_THR_STAT			0x8d044
+#define EIP197_HIA_RA_PE_CTRL			0x90010
+#define EIP197_HIA_RA_PE_STAT			0x90014
+#define EIP197_HIA_AIC_R_OFF(r)			((r) * 0x1000)
+#define EIP197_HIA_AIC_R_ENABLE_CTRL(r)		(0x9e808 - EIP197_HIA_AIC_R_OFF(r))
+#define EIP197_HIA_AIC_R_ENABLED_STAT(r)	(0x9e810 - EIP197_HIA_AIC_R_OFF(r))
+#define EIP197_HIA_AIC_R_ACK(r)			(0x9e810 - EIP197_HIA_AIC_R_OFF(r))
+#define EIP197_HIA_AIC_R_ENABLE_CLR(r)		(0x9e814 - EIP197_HIA_AIC_R_OFF(r))
+#define EIP197_HIA_AIC_G_ENABLE_CTRL		0x9f808
+#define EIP197_HIA_AIC_G_ENABLED_STAT		0x9f810
+#define EIP197_HIA_AIC_G_ACK			0x9f810
+#define EIP197_HIA_MST_CTRL			0x9fff4
+#define EIP197_HIA_OPTIONS			0x9fff8
+#define EIP197_HIA_VERSION			0x9fffc
+#define EIP197_PE_IN_DBUF_THRES			0xa0000
+#define EIP197_PE_IN_TBUF_THRES			0xa0100
+#define EIP197_PE_ICE_SCRATCH_RAM		0xa0800
+#define EIP197_PE_ICE_PUE_CTRL			0xa0c80
+#define EIP197_PE_ICE_SCRATCH_CTRL		0xa0d04
+#define EIP197_PE_ICE_FPP_CTRL			0xa0d80
+#define EIP197_PE_ICE_RAM_CTRL			0xa0ff0
+#define EIP197_PE_EIP96_FUNCTION_EN		0xa1004
+#define EIP197_PE_EIP96_CONTEXT_CTRL		0xa1008
+#define EIP197_PE_EIP96_CONTEXT_STAT		0xa100c
+#define EIP197_PE_OUT_DBUF_THRES		0xa1c00
+#define EIP197_PE_OUT_TBUF_THRES		0xa1d00
+#define EIP197_CLASSIFICATION_RAMS		0xe0000
+#define EIP197_TRC_CTRL				0xf0800
+#define EIP197_TRC_LASTRES			0xf0804
+#define EIP197_TRC_REGINDEX			0xf0808
+#define EIP197_TRC_PARAMS			0xf0820
+#define EIP197_TRC_FREECHAIN			0xf0824
+#define EIP197_TRC_PARAMS2			0xf0828
+#define EIP197_TRC_ECCCTRL			0xf0830
+#define EIP197_TRC_ECCSTAT			0xf0834
+#define EIP197_TRC_ECCADMINSTAT			0xf0838
+#define EIP197_TRC_ECCDATASTAT			0xf083c
+#define EIP197_TRC_ECCDATA			0xf0840
+#define EIP197_CS_RAM_CTRL			0xf7ff0
+#define EIP197_MST_CTRL				0xffff4
+
+/* EIP197_HIA_xDR_DESC_SIZE */
+#define EIP197_xDR_DESC_MODE_64BIT		BIT(31)
+
+/* EIP197_HIA_xDR_DMA_CFG */
+#define EIP197_HIA_xDR_WR_RES_BUF		BIT(22)
+#define EIP197_HIA_xDR_WR_CTRL_BUG		BIT(23)
+#define EIP197_HIA_xDR_WR_OWN_BUF		BIT(24)
+#define EIP197_HIA_xDR_CFG_WR_CACHE(n)		(((n) & 0x7) << 23)
+#define EIP197_HIA_xDR_CFG_RD_CACHE(n)		(((n) & 0x7) << 29)
+
+/* EIP197_HIA_CDR_THRESH */
+#define EIP197_HIA_CDR_THRESH_PROC_PKT(n)	(n)
+#define EIP197_HIA_CDR_THRESH_PROC_MODE		BIT(22)
+#define EIP197_HIA_CDR_THRESH_PKT_MODE		BIT(23)
+#define EIP197_HIA_CDR_THRESH_TIMEOUT(n)	((n) << 24) /* x256 clk cycles */
+
+/* EIP197_HIA_RDR_THRESH */
+#define EIP197_HIA_RDR_THRESH_PROC_PKT(n)	(n)
+#define EIP197_HIA_RDR_THRESH_PKT_MODE		BIT(23)
+#define EIP197_HIA_RDR_THRESH_TIMEOUT(n)	((n) << 24) /* x256 clk cycles */
+
+/* EIP197_HIA_xDR_PREP_COUNT */
+#define EIP197_xDR_PREP_CLR_COUNT		BIT(31)
+
+/* EIP197_HIA_xDR_PROC_COUNT */
+#define EIP197_xDR_PROC_xD_COUNT(n)		((n) << 2)
+#define EIP197_xDR_PROC_xD_PKT(n)		((n) << 24)
+#define EIP197_xDR_PROC_CLR_COUNT		BIT(31)
+
+/* EIP197_HIA_xDR_STAT */
+#define EIP197_xDR_DMA_ERR			BIT(0)
+#define EIP197_xDR_PREP_CMD_THRES		BIT(1)
+#define EIP197_xDR_ERR				BIT(2)
+#define EIP197_xDR_THRESH			BIT(4)
+#define EIP197_xDR_TIMEOUT			BIT(5)
+
+#define EIP197_HIA_RA_PE_CTRL_RESET		BIT(31)
+#define EIP197_HIA_RA_PE_CTRL_EN		BIT(30)
+
+/* EIP197_HIA_AIC_R_ENABLE_CTRL */
+#define EIP197_CDR_IRQ(n)			BIT((n) * 2)
+#define EIP197_RDR_IRQ(n)			BIT((n) * 2 + 1)
+
+/* EIP197_HIA_DFE/DSE_CFG */
+#define EIP197_HIA_DxE_CFG_MIN_DATA_SIZE(n)	((n) << 0)
+#define EIP197_HIA_DxE_CFG_DATA_CACHE_CTRL(n)	(((n) & 0x7) << 4)
+#define EIP197_HIA_DxE_CFG_MAX_DATA_SIZE(n)	((n) << 8)
+#define EIP197_HIA_DxE_CFG_MIN_CTRL_SIZE(n)	((n) << 16)
+#define EIP197_HIA_DxE_CFG_CTRL_CACHE_CTRL(n)	(((n) & 0x7) << 20)
+#define EIP197_HIA_DxE_CFG_MAX_CTRL_SIZE(n)	((n) << 24)
+#define EIP197_HIA_DFE_CFG_DIS_DEBUG		(BIT(31) | BIT(29))
+#define EIP197_HIA_DSE_CFG_DIS_DEBUG		BIT(31)
+
+/* EIP197_HIA_DFE/DSE_THR_CTRL */
+#define EIP197_DxE_THR_CTRL_EN			BIT(30)
+#define EIP197_DxE_THR_CTRL_RESET_PE		BIT(31)
+
+/* EIP197_HIA_AIC_G_ENABLED_STAT */
+#define EIP197_G_IRQ_DFE(n)			BIT((n) << 1)
+#define EIP197_G_IRQ_DSE(n)			BIT(((n) << 1) + 1)
+#define EIP197_G_IRQ_RING			BIT(16)
+#define EIP197_G_IRQ_PE(n)			BIT((n) + 20)
+
+/* EIP197_HIA_MST_CTRL */
+#define RD_CACHE_3BITS				0x5
+#define WR_CACHE_3BITS				0x3
+#define RD_CACHE_4BITS				(RD_CACHE_3BITS << 1 | BIT(0))
+#define WR_CACHE_4BITS				(WR_CACHE_3BITS << 1 | BIT(0))
+#define EIP197_MST_CTRL_RD_CACHE(n)		(((n) & 0xf) << 0)
+#define EIP197_MST_CTRL_WD_CACHE(n)		(((n) & 0xf) << 4)
+#define EIP197_MST_CTRL_BYTE_SWAP		BIT(24)
+#define EIP197_MST_CTRL_NO_BYTE_SWAP		BIT(25)
+
+/* EIP197_PE_IN_DBUF/TBUF_THRES */
+#define EIP197_PE_IN_xBUF_THRES_MIN(n)		((n) << 8)
+#define EIP197_PE_IN_xBUF_THRES_MAX(n)		((n) << 12)
+
+/* EIP197_PE_OUT_DBUF_THRES */
+#define EIP197_PE_OUT_DBUF_THRES_MIN(n)		((n) << 0)
+#define EIP197_PE_OUT_DBUF_THRES_MAX(n)		((n) << 4)
+
+/* EIP197_PE_ICE_SCRATCH_CTRL */
+#define EIP197_PE_ICE_SCRATCH_CTRL_CHANGE_TIMER		BIT(2)
+#define EIP197_PE_ICE_SCRATCH_CTRL_TIMER_EN		BIT(3)
+#define EIP197_PE_ICE_SCRATCH_CTRL_CHANGE_ACCESS	BIT(24)
+#define EIP197_PE_ICE_SCRATCH_CTRL_SCRATCH_ACCESS	BIT(25)
+
+/* EIP197_PE_ICE_SCRATCH_RAM */
+#define EIP197_NUM_OF_SCRATCH_BLOCKS		32
+
+/* EIP197_PE_ICE_PUE/FPP_CTRL */
+#define EIP197_PE_ICE_x_CTRL_SW_RESET			BIT(0)
+#define EIP197_PE_ICE_x_CTRL_CLR_ECC_NON_CORR		BIT(14)
+#define EIP197_PE_ICE_x_CTRL_CLR_ECC_CORR		BIT(15)
+
+/* EIP197_PE_ICE_RAM_CTRL */
+#define EIP197_PE_ICE_RAM_CTRL_PUE_PROG_EN	BIT(0)
+#define EIP197_PE_ICE_RAM_CTRL_FPP_PROG_EN	BIT(1)
+
+/* EIP197_PE_EIP96_FUNCTION_EN */
+#define EIP197_FUNCTION_RSVD			(BIT(6) | BIT(15) | BIT(20) | BIT(23))
+#define EIP197_PROTOCOL_HASH_ONLY		BIT(0)
+#define EIP197_PROTOCOL_ENCRYPT_ONLY		BIT(1)
+#define EIP197_PROTOCOL_HASH_ENCRYPT		BIT(2)
+#define EIP197_PROTOCOL_HASH_DECRYPT		BIT(3)
+#define EIP197_PROTOCOL_ENCRYPT_HASH		BIT(4)
+#define EIP197_PROTOCOL_DECRYPT_HASH		BIT(5)
+#define EIP197_ALG_ARC4				BIT(7)
+#define EIP197_ALG_AES_ECB			BIT(8)
+#define EIP197_ALG_AES_CBC			BIT(9)
+#define EIP197_ALG_AES_CTR_ICM			BIT(10)
+#define EIP197_ALG_AES_OFB			BIT(11)
+#define EIP197_ALG_AES_CFB			BIT(12)
+#define EIP197_ALG_DES_ECB			BIT(13)
+#define EIP197_ALG_DES_CBC			BIT(14)
+#define EIP197_ALG_DES_OFB			BIT(16)
+#define EIP197_ALG_DES_CFB			BIT(17)
+#define EIP197_ALG_3DES_ECB			BIT(18)
+#define EIP197_ALG_3DES_CBC			BIT(19)
+#define EIP197_ALG_3DES_OFB			BIT(21)
+#define EIP197_ALG_3DES_CFB			BIT(22)
+#define EIP197_ALG_MD5				BIT(24)
+#define EIP197_ALG_HMAC_MD5			BIT(25)
+#define EIP197_ALG_SHA1				BIT(26)
+#define EIP197_ALG_HMAC_SHA1			BIT(27)
+#define EIP197_ALG_SHA2				BIT(28)
+#define EIP197_ALG_HMAC_SHA2			BIT(29)
+#define EIP197_ALG_AES_XCBC_MAC			BIT(30)
+#define EIP197_ALG_GCM_HASH			BIT(31)
+
+/* EIP197_PE_EIP96_CONTEXT_CTRL */
+#define EIP197_CONTEXT_SIZE(n)			(n)
+#define EIP197_ADDRESS_MODE			BIT(8)
+#define EIP197_CONTROL_MODE			BIT(9)
+
+/* Context Control */
+struct safexcel_context_record {
+	u32 control0;
+	u32 control1;
+
+	__le32 data[12];
+} __packed;
+
+/* control0 */
+#define CONTEXT_CONTROL_TYPE_NULL_OUT		0x0
+#define CONTEXT_CONTROL_TYPE_NULL_IN		0x1
+#define CONTEXT_CONTROL_TYPE_HASH_OUT		0x2
+#define CONTEXT_CONTROL_TYPE_HASH_IN		0x3
+#define CONTEXT_CONTROL_TYPE_CRYPTO_OUT		0x4
+#define CONTEXT_CONTROL_TYPE_CRYPTO_IN		0x5
+#define CONTEXT_CONTROL_TYPE_ENCRYPT_HASH_OUT	0x6
+#define CONTEXT_CONTROL_TYPE_DECRYPT_HASH_IN	0x7
+#define CONTEXT_CONTROL_TYPE_HASH_ENCRYPT_OUT	0x14
+#define CONTEXT_CONTROL_TYPE_HASH_DECRYPT_OUT	0x15
+#define CONTEXT_CONTROL_RESTART_HASH		BIT(4)
+#define CONTEXT_CONTROL_NO_FINISH_HASH		BIT(5)
+#define CONTEXT_CONTROL_SIZE(n)			((n) << 8)
+#define CONTEXT_CONTROL_KEY_EN			BIT(16)
+#define CONTEXT_CONTROL_CRYPTO_ALG_AES128	(0x5 << 17)
+#define CONTEXT_CONTROL_CRYPTO_ALG_AES192	(0x6 << 17)
+#define CONTEXT_CONTROL_CRYPTO_ALG_AES256	(0x7 << 17)
+#define CONTEXT_CONTROL_DIGEST_PRECOMPUTED	(0x1 << 21)
+#define CONTEXT_CONTROL_DIGEST_HMAC		(0x3 << 21)
+#define CONTEXT_CONTROL_CRYPTO_ALG_SHA1		(0x2 << 23)
+#define CONTEXT_CONTROL_CRYPTO_ALG_SHA224	(0x4 << 23)
+#define CONTEXT_CONTROL_CRYPTO_ALG_SHA256	(0x3 << 23)
+#define CONTEXT_CONTROL_INV_FR			(0x5 << 24)
+#define CONTEXT_CONTROL_INV_TR			(0x6 << 24)
+
+/* control1 */
+#define CONTEXT_CONTROL_CRYPTO_MODE_ECB		(0 << 0)
+#define CONTEXT_CONTROL_CRYPTO_MODE_CBC		(1 << 0)
+#define CONTEXT_CONTROL_IV0			BIT(5)
+#define CONTEXT_CONTROL_IV1			BIT(6)
+#define CONTEXT_CONTROL_IV2			BIT(7)
+#define CONTEXT_CONTROL_IV3			BIT(8)
+#define CONTEXT_CONTROL_DIGEST_CNT		BIT(9)
+#define CONTEXT_CONTROL_COUNTER_MODE		BIT(10)
+#define CONTEXT_CONTROL_HASH_STORE		BIT(19)
+
+/* EIP197_CS_RAM_CTRL */
+#define EIP197_TRC_ENABLE_0			BIT(4)
+#define EIP197_TRC_ENABLE_1			BIT(5)
+#define EIP197_TRC_ENABLE_2			BIT(6)
+#define EIP197_TRC_ENABLE_MASK			GENMASK(6, 4)
+
+/* EIP197_TRC_PARAMS */
+#define EIP197_TRC_PARAMS_SW_RESET		BIT(0)
+#define EIP197_TRC_PARAMS_DATA_ACCESS		BIT(2)
+#define EIP197_TRC_PARAMS_HTABLE_SZ(x)		((x) << 4)
+#define EIP197_TRC_PARAMS_BLK_TIMER_SPEED(x)	((x) << 10)
+#define EIP197_TRC_PARAMS_RC_SZ_LARGE(n)	((n) << 18)
+
+/* EIP197_TRC_FREECHAIN */
+#define EIP197_TRC_FREECHAIN_HEAD_PTR(p)	(p)
+#define EIP197_TRC_FREECHAIN_TAIL_PTR(p)	((p) << 16)
+
+/* EIP197_TRC_PARAMS2 */
+#define EIP197_TRC_PARAMS2_HTABLE_PTR(p)	(p)
+#define EIP197_TRC_PARAMS2_RC_SZ_SMALL(n)	((n) << 18)
+
+/* Cache helpers */
+#define EIP197_CS_RC_MAX			52
+#define EIP197_CS_RC_SIZE			(4 * sizeof(u32))
+#define EIP197_CS_RC_NEXT(x)			(x)
+#define EIP197_CS_RC_PREV(x)			((x) << 10)
+#define EIP197_RC_NULL				0x3ff
+#define EIP197_CS_TRC_REC_WC			59
+#define EIP197_CS_TRC_LG_REC_WC			73
+
+/* Result data */
+struct result_data_desc {
+	u32 packet_length:17;
+	u32 error_code:15;
+
+	u8 bypass_length:4;
+	u8 e15:1;
+	u16 rsvd0;
+	u8 hash_bytes:1;
+	u8 hash_length:6;
+	u8 generic_bytes:1;
+	u8 checksum:1;
+	u8 next_header:1;
+	u8 length:1;
+
+	u16 application_id;
+	u16 rsvd1;
+
+	u32 rsvd2;
+} __packed;
+
+
+/* Basic Result Descriptor format */
+struct safexcel_result_desc {
+	u32 particle_size:17;
+	u8 rsvd0:3;
+	u8 descriptor_overflow:1;
+	u8 buffer_overflow:1;
+	u8 last_seg:1;
+	u8 first_seg:1;
+	u16 result_size:8;
+
+	u32 rsvd1;
+
+	u32 data_lo;
+	u32 data_hi;
+
+	struct result_data_desc result_data;
+} __packed;
+
+struct safexcel_token {
+	u32 packet_length:17;
+	u8 stat:2;
+	u16 instructions:9;
+	u8 opcode:4;
+} __packed;
+
+#define EIP197_TOKEN_STAT_LAST_HASH		BIT(0)
+#define EIP197_TOKEN_STAT_LAST_PACKET		BIT(1)
+#define EIP197_TOKEN_OPCODE_DIRECTION		0x0
+#define EIP197_TOKEN_OPCODE_INSERT		0x2
+#define EIP197_TOKEN_OPCODE_NOOP		EIP197_TOKEN_OPCODE_INSERT
+#define EIP197_TOKEN_OPCODE_BYPASS		GENMASK(3, 0)
+
+static inline void eip197_noop_token(struct safexcel_token *token)
+{
+	token->opcode = EIP197_TOKEN_OPCODE_NOOP;
+	token->packet_length = BIT(2);
+}
+
+/* Instructions */
+#define EIP197_TOKEN_INS_INSERT_HASH_DIGEST	0x1c
+#define EIP197_TOKEN_INS_TYPE_OUTPUT		BIT(5)
+#define EIP197_TOKEN_INS_TYPE_HASH		BIT(6)
+#define EIP197_TOKEN_INS_TYPE_CRYTO		BIT(7)
+#define EIP197_TOKEN_INS_LAST			BIT(8)
+
+/* Processing Engine Control Data  */
+struct safexcel_control_data_desc {
+	u32 packet_length:17;
+	u16 options:13;
+	u8 type:2;
+
+	u16 application_id;
+	u16 rsvd;
+
+	u8 refresh:2;
+	u32 context_lo:30;
+	u32 context_hi;
+
+	u32 control0;
+	u32 control1;
+
+	u32 token[EIP197_MAX_TOKENS];
+} __packed;
+
+#define EIP197_OPTION_MAGIC_VALUE	BIT(0)
+#define EIP197_OPTION_64BIT_CTX		BIT(1)
+#define EIP197_OPTION_CTX_CTRL_IN_CMD	BIT(8)
+#define EIP197_OPTION_4_TOKEN_IV_CMD	GENMASK(11, 9)
+
+#define EIP197_TYPE_EXTENDED		0x3
+
+/* Basic Command Descriptor format */
+struct safexcel_command_desc {
+	u32 particle_size:17;
+	u8 rsvd0:5;
+	u8 last_seg:1;
+	u8 first_seg:1;
+	u16 additional_cdata_size:8;
+
+	u32 rsvd1;
+
+	u32 data_lo;
+	u32 data_hi;
+
+	struct safexcel_control_data_desc control_data;
+} __packed;
+
+/*
+ * Internal structures & functions
+ */
+
+enum eip197_fw {
+	FW_IFPP = 0,
+	FW_IPUE,
+	FW_NB
+};
+
+struct safexcel_ring {
+	void *base;
+	void *base_end;
+	dma_addr_t base_dma;
+
+	/* write and read pointers */
+	void *write;
+	void *read;
+
+	/* number of elements used in the ring */
+	unsigned nr;
+	unsigned offset;
+};
+
+enum safexcel_alg_type {
+	SAFEXCEL_ALG_TYPE_SKCIPHER,
+	SAFEXCEL_ALG_TYPE_AHASH,
+};
+
+struct safexcel_request {
+	struct list_head list;
+	struct crypto_async_request *req;
+};
+
+struct safexcel_config {
+	u32 rings;
+
+	u32 cd_size;
+	u32 cd_offset;
+
+	u32 rd_size;
+	u32 rd_offset;
+};
+
+struct safexcel_work_data {
+	struct work_struct work;
+	struct safexcel_crypto_priv *priv;
+	int ring;
+};
+
+struct safexcel_crypto_priv {
+	void __iomem *base;
+	struct device *dev;
+	struct clk *clk;
+	struct safexcel_config config;
+
+	spinlock_t lock;
+	struct crypto_queue queue;
+
+	bool need_dequeue;
+
+	/* context DMA pool */
+	struct dma_pool *context_pool;
+
+	atomic_t ring_used;
+
+	struct {
+		spinlock_t lock;
+		spinlock_t egress_lock;
+
+		struct list_head list;
+		struct workqueue_struct *workqueue;
+		struct safexcel_work_data work_data;
+
+		/* command/result rings */
+		struct safexcel_ring cdr;
+		struct safexcel_ring rdr;
+	} ring[EIP197_MAX_RINGS];
+};
+
+struct safexcel_context {
+	int (*send)(struct crypto_async_request *req, int ring,
+		    struct safexcel_request *request, int *commands,
+		    int *results);
+	int (*handle_result)(struct safexcel_crypto_priv *priv, int ring,
+			     struct crypto_async_request *req, bool *complete,
+			     int *ret);
+	struct safexcel_context_record *ctxr;
+	dma_addr_t ctxr_dma;
+
+	int ring;
+	bool needs_inv;
+	bool exit_inv;
+
+	/* Used for ahash requests */
+	dma_addr_t result_dma;
+	void *cache;
+	dma_addr_t cache_dma;
+	unsigned int cache_sz;
+};
+
+/*
+ * Template structure to describe the algorithms in order to register them.
+ * It also has the purpose to contain our private structure and is actually
+ * the only way I know in this framework to avoid having global pointers...
+ */
+struct safexcel_alg_template {
+	struct safexcel_crypto_priv *priv;
+	enum safexcel_alg_type type;
+	union {
+		struct skcipher_alg skcipher;
+		struct ahash_alg ahash;
+	} alg;
+};
+
+struct safexcel_inv_result {
+	struct completion completion;
+	int error;
+};
+
+void safexcel_dequeue(struct safexcel_crypto_priv *priv);
+void safexcel_complete(struct safexcel_crypto_priv *priv, int ring);
+void safexcel_free_context(struct safexcel_crypto_priv *priv,
+				  struct crypto_async_request *req,
+				  int result_sz);
+int safexcel_invalidate_cache(struct crypto_async_request *async,
+			      struct safexcel_context *ctx,
+			      struct safexcel_crypto_priv *priv,
+			      dma_addr_t ctxr_dma, int ring,
+			      struct safexcel_request *request);
+int safexcel_init_ring_descriptors(struct safexcel_crypto_priv *priv,
+				   struct safexcel_ring *cdr,
+				   struct safexcel_ring *rdr);
+int safexcel_select_ring(struct safexcel_crypto_priv *priv);
+void *safexcel_ring_next_rptr(struct safexcel_crypto_priv *priv,
+			      struct safexcel_ring *ring);
+void safexcel_ring_rollback_wptr(struct safexcel_crypto_priv *priv,
+				 struct safexcel_ring *ring);
+struct safexcel_command_desc *safexcel_add_cdesc(struct safexcel_crypto_priv *priv,
+						 int ring_id,
+						 bool first, bool last,
+						 dma_addr_t data, u32 len,
+						 u32 full_data_len,
+						 dma_addr_t context);
+struct safexcel_result_desc *safexcel_add_rdesc(struct safexcel_crypto_priv *priv,
+						 int ring_id,
+						bool first, bool last,
+						dma_addr_t data, u32 len);
+void safexcel_inv_complete(struct crypto_async_request *req, int error);
+
+/* available algorithms */
+extern struct safexcel_alg_template safexcel_alg_ecb_aes;
+extern struct safexcel_alg_template safexcel_alg_cbc_aes;
+extern struct safexcel_alg_template safexcel_alg_sha1;
+extern struct safexcel_alg_template safexcel_alg_sha224;
+extern struct safexcel_alg_template safexcel_alg_sha256;
+extern struct safexcel_alg_template safexcel_alg_hmac_sha1;
+
+#endif

drivers/crypto/inside-secure/safexcel_cipher.c

+/*
+ * Copyright (C) 2017 Marvell
+ *
+ * Antoine Tenart <antoine.tenart@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmapool.h>
+
+#include <crypto/aes.h>
+#include <crypto/skcipher.h>
+
+#include "safexcel.h"
+
+enum safexcel_cipher_direction {
+	SAFEXCEL_ENCRYPT,
+	SAFEXCEL_DECRYPT,
+};
+
+struct safexcel_cipher_ctx {
+	struct safexcel_context base;
+	struct safexcel_crypto_priv *priv;
+
+	enum safexcel_cipher_direction direction;
+	u32 mode;
+
+	__le32 key[8];
+	unsigned int key_len;
+};
+
+static void safexcel_cipher_token(struct safexcel_cipher_ctx *ctx,
+				  struct crypto_async_request *async,
+				  struct safexcel_command_desc *cdesc,
+				  u32 length)
+{
+	struct skcipher_request *req = skcipher_request_cast(async);
+	struct safexcel_token *token;
+	unsigned offset = 0;
+
+	if (ctx->mode == CONTEXT_CONTROL_CRYPTO_MODE_CBC) {
+		offset = AES_BLOCK_SIZE / sizeof(u32);
+		memcpy(cdesc->control_data.token, req->iv, AES_BLOCK_SIZE);
+
+		cdesc->control_data.options |= EIP197_OPTION_4_TOKEN_IV_CMD;
+	}
+
+	token = (struct safexcel_token *)(cdesc->control_data.token + offset);
+
+	token[0].opcode = EIP197_TOKEN_OPCODE_DIRECTION;
+	token[0].packet_length = length;
+	token[0].stat = EIP197_TOKEN_STAT_LAST_PACKET;
+	token[0].instructions = EIP197_TOKEN_INS_LAST |
+				EIP197_TOKEN_INS_TYPE_CRYTO |
+				EIP197_TOKEN_INS_TYPE_OUTPUT;
+}
+
+static int safexcel_aes_setkey(struct crypto_skcipher *ctfm, const u8 *key,
+			       unsigned int len)
+{
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(ctfm);
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct crypto_aes_ctx aes;
+	int ret, i;
+
+	ret = crypto_aes_expand_key(&aes, key, len);
+	if (ret) {
+		crypto_skcipher_set_flags(ctfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return ret;
+	}
+
+	for (i = 0; i < len / sizeof(u32); i++) {
+		if (ctx->key[i] != cpu_to_le32(aes.key_enc[i])) {
+			ctx->base.needs_inv = true;
+			break;
+		}
+	}
+
+	for (i = 0; i < len / sizeof(u32); i++)
+		ctx->key[i] = cpu_to_le32(aes.key_enc[i]);
+
+	ctx->key_len = len;
+
+	memzero_explicit(&aes, sizeof(aes));
+	return 0;
+}
+
+static int safexcel_context_control(struct safexcel_cipher_ctx *ctx,
+				    struct safexcel_command_desc *cdesc)
+{
+	struct safexcel_crypto_priv *priv = ctx->priv;
+	int ctrl_size;
+
+	if (ctx->direction == SAFEXCEL_ENCRYPT)
+		cdesc->control_data.control0 |= CONTEXT_CONTROL_TYPE_CRYPTO_OUT;
+	else
+		cdesc->control_data.control0 |= CONTEXT_CONTROL_TYPE_CRYPTO_IN;
+
+	cdesc->control_data.control0 |= CONTEXT_CONTROL_KEY_EN;
+	cdesc->control_data.control1 |= ctx->mode;
+
+	switch (ctx->key_len) {
+	case AES_KEYSIZE_128:
+		cdesc->control_data.control0 |= CONTEXT_CONTROL_CRYPTO_ALG_AES128;
+		ctrl_size = 4;
+		break;
+	case AES_KEYSIZE_192:
+		cdesc->control_data.control0 |= CONTEXT_CONTROL_CRYPTO_ALG_AES192;
+		ctrl_size = 6;
+		break;
+	case AES_KEYSIZE_256:
+		cdesc->control_data.control0 |= CONTEXT_CONTROL_CRYPTO_ALG_AES256;
+		ctrl_size = 8;
+		break;
+	default:
+		dev_err(priv->dev, "aes keysize not supported: %u\n",
+			ctx->key_len);
+		return -EINVAL;
+	}
+	cdesc->control_data.control0 |= CONTEXT_CONTROL_SIZE(ctrl_size);
+
+	return 0;
+}
+
+static int safexcel_handle_result(struct safexcel_crypto_priv *priv, int ring,
+				  struct crypto_async_request *async,
+				  bool *should_complete, int *ret)
+{
+	struct skcipher_request *req = skcipher_request_cast(async);
+	struct safexcel_result_desc *rdesc;
+	int ndesc = 0;
+
+	*ret = 0;
+
+	spin_lock_bh(&priv->ring[ring].egress_lock);
+	do {
+		rdesc = safexcel_ring_next_rptr(priv, &priv->ring[ring].rdr);
+		if (IS_ERR(rdesc)) {
+			dev_err(priv->dev,
+				"cipher: result: could not retrieve the result descriptor\n");
+			*ret = PTR_ERR(rdesc);
+			break;
+		}
+
+		if (rdesc->result_data.error_code) {
+			dev_err(priv->dev,
+				"cipher: result: result descriptor error (%d)\n",
+				rdesc->result_data.error_code);
+			*ret = -EIO;
+		}
+
+		ndesc++;
+	} while (!rdesc->last_seg);
+
+	safexcel_complete(priv, ring);
+	spin_unlock_bh(&priv->ring[ring].egress_lock);
+
+	if (req->src == req->dst) {
+		dma_unmap_sg(priv->dev, req->src,
+			     sg_nents_for_len(req->src, req->cryptlen),
+			     DMA_BIDIRECTIONAL);
+	} else {
+		dma_unmap_sg(priv->dev, req->src,
+			     sg_nents_for_len(req->src, req->cryptlen),
+			     DMA_TO_DEVICE);
+		dma_unmap_sg(priv->dev, req->dst,
+			     sg_nents_for_len(req->dst, req->cryptlen),
+			     DMA_FROM_DEVICE);
+	}
+
+	*should_complete = true;
+
+	return ndesc;
+}
+
+static int safexcel_aes_send(struct crypto_async_request *async,
+			     int ring, struct safexcel_request *request,
+			     int *commands, int *results)
+{
+	struct skcipher_request *req = skcipher_request_cast(async);
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
+	struct safexcel_crypto_priv *priv = ctx->priv;
+	struct safexcel_command_desc *cdesc;
+	struct safexcel_result_desc *rdesc;
+	struct scatterlist *sg;
+	int nr_src, nr_dst, n_cdesc = 0, n_rdesc = 0, queued = req->cryptlen;
+	int i, ret = 0;
+
+	request->req = &req->base;
+
+	if (req->src == req->dst) {
+		nr_src = dma_map_sg(priv->dev, req->src,
+				    sg_nents_for_len(req->src, req->cryptlen),
+				    DMA_BIDIRECTIONAL);
+		nr_dst = nr_src;
+		if (!nr_src)
+			return -EINVAL;
+	} else {
+		nr_src = dma_map_sg(priv->dev, req->src,
+				    sg_nents_for_len(req->src, req->cryptlen),
+				    DMA_TO_DEVICE);
+		if (!nr_src)
+			return -EINVAL;
+
+		nr_dst = dma_map_sg(priv->dev, req->dst,
+				    sg_nents_for_len(req->dst, req->cryptlen),
+				    DMA_FROM_DEVICE);
+		if (!nr_dst) {
+			dma_unmap_sg(priv->dev, req->src,
+				     sg_nents_for_len(req->src, req->cryptlen),
+				     DMA_TO_DEVICE);
+			return -EINVAL;
+		}
+	}
+
+	memcpy(ctx->base.ctxr->data, ctx->key, ctx->key_len);
+
+	spin_lock_bh(&priv->ring[ring].egress_lock);
+
+	/* command descriptors */
+	for_each_sg(req->src, sg, nr_src, i) {
+		int len = sg_dma_len(sg);
+
+		/* Do not overflow the request */
+		if (queued - len < 0)
+			len = queued;
+
+		cdesc = safexcel_add_cdesc(priv, ring, !n_cdesc, !(queued - len),
+					   sg_dma_address(sg), len, req->cryptlen,
+					   ctx->base.ctxr_dma);
+		if (IS_ERR(cdesc)) {
+			/* No space left in the command descriptor ring */
+			ret = PTR_ERR(cdesc);
+			goto cdesc_rollback;
+		}
+		n_cdesc++;
+
+		if (n_cdesc == 1) {
+			safexcel_context_control(ctx, cdesc);
+			safexcel_cipher_token(ctx, async, cdesc, req->cryptlen);
+		}
+
+		queued -= len;
+		if (!queued)
+			break;
+	}
+
+	/* result descriptors */
+	for_each_sg(req->dst, sg, nr_dst, i) {
+		bool first = !i, last = (i == nr_dst - 1);
+		u32 len = sg_dma_len(sg);
+
+		rdesc = safexcel_add_rdesc(priv, ring, first, last,
+					   sg_dma_address(sg), len);
+		if (IS_ERR(rdesc)) {
+			/* No space left in the result descriptor ring */
+			ret = PTR_ERR(rdesc);
+			goto rdesc_rollback;
+		}
+		n_rdesc++;
+	}
+
+	ctx->base.handle_result = safexcel_handle_result;
+
+	spin_unlock_bh(&priv->ring[ring].egress_lock);
+
+	*commands = n_cdesc;
+	*results = nr_dst;
+	return 0;
+
+rdesc_rollback:
+	for (i = 0; i < n_rdesc; i++)
+		safexcel_ring_rollback_wptr(priv, &priv->ring[ring].rdr);
+cdesc_rollback:
+	for (i = 0; i < n_cdesc; i++)
+		safexcel_ring_rollback_wptr(priv, &priv->ring[ring].cdr);
+
+	spin_unlock_bh(&priv->ring[ring].egress_lock);
+
+	if (req->src == req->dst) {
+		dma_unmap_sg(priv->dev, req->src,
+			     sg_nents_for_len(req->src, req->cryptlen),
+			     DMA_BIDIRECTIONAL);
+	} else {
+		dma_unmap_sg(priv->dev, req->src,
+			     sg_nents_for_len(req->src, req->cryptlen),
+			     DMA_TO_DEVICE);
+		dma_unmap_sg(priv->dev, req->dst,
+			     sg_nents_for_len(req->dst, req->cryptlen),
+			     DMA_FROM_DEVICE);
+	}
+
+	return ret;
+}
+
+static int safexcel_handle_inv_result(struct safexcel_crypto_priv *priv,
+				      int ring,
+				      struct crypto_async_request *async,
+				      bool *should_complete, int *ret)
+{
+	struct skcipher_request *req = skcipher_request_cast(async);
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
+	struct safexcel_result_desc *rdesc;
+	int ndesc = 0, enq_ret;
+
+	*ret = 0;
+
+	spin_lock_bh(&priv->ring[ring].egress_lock);
+	do {
+		rdesc = safexcel_ring_next_rptr(priv, &priv->ring[ring].rdr);
+		if (IS_ERR(rdesc)) {
+			dev_err(priv->dev,
+				"cipher: invalidate: could not retrieve the result descriptor\n");
+			*ret = PTR_ERR(rdesc);
+			break;
+		}
+
+		if (rdesc->result_data.error_code) {
+			dev_err(priv->dev, "cipher: invalidate: result descriptor error (%d)\n",
+				rdesc->result_data.error_code);
+			*ret = -EIO;
+		}
+
+		ndesc++;
+	} while (!rdesc->last_seg);
+
+	safexcel_complete(priv, ring);
+	spin_unlock_bh(&priv->ring[ring].egress_lock);
+
+	if (ctx->base.exit_inv) {
+		dma_pool_free(priv->context_pool, ctx->base.ctxr,
+			      ctx->base.ctxr_dma);
+
+		*should_complete = true;
+
+		return ndesc;
+	}
+
+	ctx->base.needs_inv = false;
+	ctx->base.ring = safexcel_select_ring(priv);
+	ctx->base.send = safexcel_aes_send;
+
+	spin_lock_bh(&priv->lock);
+	enq_ret = crypto_enqueue_request(&priv->queue, async);
+	spin_unlock_bh(&priv->lock);
+
+	if (enq_ret != -EINPROGRESS)
+		*ret = enq_ret;
+
+	priv->need_dequeue = true;
+	*should_complete = false;
+
+	return ndesc;
+}
+
+static int safexcel_cipher_send_inv(struct crypto_async_request *async,
+				    int ring, struct safexcel_request *request,
+				    int *commands, int *results)
+{
+	struct skcipher_request *req = skcipher_request_cast(async);
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
+	struct safexcel_crypto_priv *priv = ctx->priv;
+	int ret;
+
+	ctx->base.handle_result = safexcel_handle_inv_result;
+
+	ret = safexcel_invalidate_cache(async, &ctx->base, priv,
+					ctx->base.ctxr_dma, ring, request);
+	if (unlikely(ret))
+		return ret;
+
+	*commands = 1;
+	*results = 1;
+
+	return 0;
+}
+
+static int safexcel_cipher_exit_inv(struct crypto_tfm *tfm)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct safexcel_crypto_priv *priv = ctx->priv;
+	struct skcipher_request req;
+	struct safexcel_inv_result result = { 0 };
+
+	memset(&req, 0, sizeof(struct skcipher_request));
+
+	/* create invalidation request */
+	init_completion(&result.completion);
+	skcipher_request_set_callback(&req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+					safexcel_inv_complete, &result);
+
+	skcipher_request_set_tfm(&req, __crypto_skcipher_cast(tfm));
+	ctx = crypto_tfm_ctx(req.base.tfm);
+	ctx->base.exit_inv = true;
+	ctx->base.send = safexcel_cipher_send_inv;
+
+	spin_lock_bh(&priv->lock);
+	crypto_enqueue_request(&priv->queue, &req.base);
+	spin_unlock_bh(&priv->lock);
+
+	if (!priv->need_dequeue)
+		safexcel_dequeue(priv);
+
+	wait_for_completion_interruptible(&result.completion);
+
+	if (result.error) {
+		dev_warn(priv->dev,
+			"cipher: sync: invalidate: completion error %d\n",
+			 result.error);
+		return result.error;
+	}
+
+	return 0;
+}
+
+static int safexcel_aes(struct skcipher_request *req,
+			enum safexcel_cipher_direction dir, u32 mode)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
+	struct safexcel_crypto_priv *priv = ctx->priv;
+	int ret;
+
+	ctx->direction = dir;
+	ctx->mode = mode;
+
+	if (ctx->base.ctxr) {
+		if (ctx->base.needs_inv)
+			ctx->base.send = safexcel_cipher_send_inv;
+	} else {
+		ctx->base.ring = safexcel_select_ring(priv);
+		ctx->base.send = safexcel_aes_send;
+
+		ctx->base.ctxr = dma_pool_zalloc(priv->context_pool,
+						 EIP197_GFP_FLAGS(req->base),
+						 &ctx->base.ctxr_dma);
+		if (!ctx->base.ctxr)
+			return -ENOMEM;
+	}
+
+	spin_lock_bh(&priv->lock);
+	ret = crypto_enqueue_request(&priv->queue, &req->base);
+	spin_unlock_bh(&priv->lock);
+
+	if (!priv->need_dequeue)
+		safexcel_dequeue(priv);
+
+	return ret;
+}
+
+static int safexcel_ecb_aes_encrypt(struct skcipher_request *req)
+{
+	return safexcel_aes(req, SAFEXCEL_ENCRYPT,
+			    CONTEXT_CONTROL_CRYPTO_MODE_ECB);
+}
+
+static int safexcel_ecb_aes_decrypt(struct skcipher_request *req)
+{
+	return safexcel_aes(req, SAFEXCEL_DECRYPT,
+			    CONTEXT_CONTROL_CRYPTO_MODE_ECB);
+}
+
+static int safexcel_skcipher_cra_init(struct crypto_tfm *tfm)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct safexcel_alg_template *tmpl =
+		container_of(tfm->__crt_alg, struct safexcel_alg_template,
+			     alg.skcipher.base);
+
+	ctx->priv = tmpl->priv;
+
+	return 0;
+}
+
+static void safexcel_skcipher_cra_exit(struct crypto_tfm *tfm)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct safexcel_crypto_priv *priv = ctx->priv;
+	int ret;
+
+	memzero_explicit(ctx->key, 8 * sizeof(u32));
+
+	/* context not allocated, skip invalidation */
+	if (!ctx->base.ctxr)
+		return;
+
+	memzero_explicit(ctx->base.ctxr->data, 8 * sizeof(u32));
+
+	ret = safexcel_cipher_exit_inv(tfm);
+	if (ret)
+		dev_warn(priv->dev, "cipher: invalidation error %d\n", ret);
+}
+
+struct safexcel_alg_template safexcel_alg_ecb_aes = {
+	.type = SAFEXCEL_ALG_TYPE_SKCIPHER,
+	.alg.skcipher = {
+		.setkey = safexcel_aes_setkey,
+		.encrypt = safexcel_ecb_aes_encrypt,
+		.decrypt = safexcel_ecb_aes_decrypt,
+		.min_keysize = AES_MIN_KEY_SIZE,
+		.max_keysize = AES_MAX_KEY_SIZE,
+		.base = {
+			.cra_name = "ecb(aes)",
+			.cra_driver_name = "safexcel-ecb-aes",
+			.cra_priority = 300,
+			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER | CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = AES_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_skcipher_cra_init,
+			.cra_exit = safexcel_skcipher_cra_exit,
+			.cra_module = THIS_MODULE,
+		},
+	},
+};
+
+static int safexcel_cbc_aes_encrypt(struct skcipher_request *req)
+{
+	return safexcel_aes(req, SAFEXCEL_ENCRYPT,
+			    CONTEXT_CONTROL_CRYPTO_MODE_CBC);
+}
+
+static int safexcel_cbc_aes_decrypt(struct skcipher_request *req)
+{
+	return safexcel_aes(req, SAFEXCEL_DECRYPT,
+			    CONTEXT_CONTROL_CRYPTO_MODE_CBC);
+}
+
+struct safexcel_alg_template safexcel_alg_cbc_aes = {
+	.type = SAFEXCEL_ALG_TYPE_SKCIPHER,
+	.alg.skcipher = {
+		.setkey = safexcel_aes_setkey,
+		.encrypt = safexcel_cbc_aes_encrypt,
+		.decrypt = safexcel_cbc_aes_decrypt,
+		.min_keysize = AES_MIN_KEY_SIZE,
+		.max_keysize = AES_MAX_KEY_SIZE,
+		.ivsize = AES_BLOCK_SIZE,
+		.base = {
+			.cra_name = "cbc(aes)",
+			.cra_driver_name = "safexcel-cbc-aes",
+			.cra_priority = 300,
+			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER | CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = AES_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_skcipher_cra_init,
+			.cra_exit = safexcel_skcipher_cra_exit,
+			.cra_module = THIS_MODULE,
+		},
+	},
+};

drivers/crypto/inside-secure/safexcel_hash.c

+/*
+ * Copyright (C) 2017 Marvell
+ *
+ * Antoine Tenart <antoine.tenart@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <crypto/sha.h>
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmapool.h>
+
+
+#include "safexcel.h"
+
+struct safexcel_ahash_ctx {
+	struct safexcel_context base;
+	struct safexcel_crypto_priv *priv;
+
+	u32 alg;
+	u32 digest;
+
+	u32 ipad[SHA1_DIGEST_SIZE / sizeof(u32)];
+	u32 opad[SHA1_DIGEST_SIZE / sizeof(u32)];
+};
+
+struct safexcel_ahash_req {
+	bool last_req;
+	bool finish;
+	bool hmac;
+
+	u8 state_sz;    /* expected sate size, only set once */
+	u32 state[SHA256_DIGEST_SIZE / sizeof(u32)];
+
+	u64 len;
+	u64 processed;
+
+	u8 cache[SHA256_BLOCK_SIZE] __aligned(sizeof(u32));
+	u8 cache_next[SHA256_BLOCK_SIZE] __aligned(sizeof(u32));
+};
+
+struct safexcel_ahash_export_state {
+	u64 len;
+	u64 processed;
+
+	u32 state[SHA256_DIGEST_SIZE / sizeof(u32)];
+	u8 cache[SHA256_BLOCK_SIZE];
+};
+
+static void safexcel_hash_token(struct safexcel_command_desc *cdesc,
+				u32 input_length, u32 result_length)
+{
+	struct safexcel_token *token =
+		(struct safexcel_token *)cdesc->control_data.token;
+
+	token[0].opcode = EIP197_TOKEN_OPCODE_DIRECTION;
+	token[0].packet_length = input_length;
+	token[0].stat = EIP197_TOKEN_STAT_LAST_HASH;
+	token[0].instructions = EIP197_TOKEN_INS_TYPE_HASH;
+
+	token[1].opcode = EIP197_TOKEN_OPCODE_INSERT;
+	token[1].packet_length = result_length;
+	token[1].stat = EIP197_TOKEN_STAT_LAST_HASH |
+			EIP197_TOKEN_STAT_LAST_PACKET;
+	token[1].instructions = EIP197_TOKEN_INS_TYPE_OUTPUT |
+				EIP197_TOKEN_INS_INSERT_HASH_DIGEST;
+}
+
+static void safexcel_context_control(struct safexcel_ahash_ctx *ctx,
+				     struct safexcel_ahash_req *req,
+				     struct safexcel_command_desc *cdesc,
+				     unsigned int digestsize,
+				     unsigned int blocksize)
+{
+	int i;
+
+	cdesc->control_data.control0 |= CONTEXT_CONTROL_TYPE_HASH_OUT;
+	cdesc->control_data.control0 |= ctx->alg;
+	cdesc->control_data.control0 |= ctx->digest;
+
+	if (ctx->digest == CONTEXT_CONTROL_DIGEST_PRECOMPUTED) {
+		if (req->processed) {
+			if (ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA1)
+				cdesc->control_data.control0 |= CONTEXT_CONTROL_SIZE(6);
+			else if (ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA224 ||
+				 ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA256)
+				cdesc->control_data.control0 |= CONTEXT_CONTROL_SIZE(9);
+
+			cdesc->control_data.control1 |= CONTEXT_CONTROL_DIGEST_CNT;
+		} else {
+			cdesc->control_data.control0 |= CONTEXT_CONTROL_RESTART_HASH;
+		}
+
+		if (!req->finish)
+			cdesc->control_data.control0 |= CONTEXT_CONTROL_NO_FINISH_HASH;
+
+		/*
+		 * Copy the input digest if needed, and setup the context
+		 * fields. Do this now as we need it to setup the first command
+		 * descriptor.
+		 */
+		if (req->processed) {
+			for (i = 0; i < digestsize / sizeof(u32); i++)
+				ctx->base.ctxr->data[i] = cpu_to_le32(req->state[i]);
+
+			if (req->finish)
+				ctx->base.ctxr->data[i] = cpu_to_le32(req->processed / blocksize);
+		}
+	} else if (ctx->digest == CONTEXT_CONTROL_DIGEST_HMAC) {
+		cdesc->control_data.control0 |= CONTEXT_CONTROL_SIZE(10);
+
+		memcpy(ctx->base.ctxr->data, ctx->ipad, digestsize);
+		memcpy(ctx->base.ctxr->data + digestsize / sizeof(u32),
+		       ctx->opad, digestsize);
+	}
+}
+
+static int safexcel_handle_result(struct safexcel_crypto_priv *priv, int ring,
+				  struct crypto_async_request *async,
+				  bool *should_complete, int *ret)
+{
+	struct safexcel_result_desc *rdesc;
+	struct ahash_request *areq = ahash_request_cast(async);
+	struct crypto_ahash *ahash = crypto_ahash_reqtfm(areq);
+	struct safexcel_ahash_req *sreq = ahash_request_ctx(areq);
+	int cache_len, result_sz = sreq->state_sz;
+
+	*ret = 0;
+
+	spin_lock_bh(&priv->ring[ring].egress_lock);
+	rdesc = safexcel_ring_next_rptr(priv, &priv->ring[ring].rdr);
+	if (IS_ERR(rdesc)) {
+		dev_err(priv->dev,
+			"hash: result: could not retrieve the result descriptor\n");
+		*ret = PTR_ERR(rdesc);
+	} else if (rdesc->result_data.error_code) {
+		dev_err(priv->dev,
+			"hash: result: result descriptor error (%d)\n",
+			rdesc->result_data.error_code);
+		*ret = -EINVAL;
+	}
+
+	safexcel_complete(priv, ring);
+	spin_unlock_bh(&priv->ring[ring].egress_lock);
+
+	if (sreq->finish)
+		result_sz = crypto_ahash_digestsize(ahash);
+	memcpy(sreq->state, areq->result, result_sz);
+
+	dma_unmap_sg(priv->dev, areq->src,
+		     sg_nents_for_len(areq->src, areq->nbytes), DMA_TO_DEVICE);
+
+	safexcel_free_context(priv, async, sreq->state_sz);
+
+	cache_len = sreq->len - sreq->processed;
+	if (cache_len)
+		memcpy(sreq->cache, sreq->cache_next, cache_len);
+
+	*should_complete = true;
+
+	return 1;
+}
+
+static int safexcel_ahash_send(struct crypto_async_request *async, int ring,
+			       struct safexcel_request *request, int *commands,
+			       int *results)
+{
+	struct ahash_request *areq = ahash_request_cast(async);
+	struct crypto_ahash *ahash = crypto_ahash_reqtfm(areq);
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
+	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(crypto_ahash_reqtfm(areq));
+	struct safexcel_crypto_priv *priv = ctx->priv;
+	struct safexcel_command_desc *cdesc, *first_cdesc = NULL;
+	struct safexcel_result_desc *rdesc;
+	struct scatterlist *sg;
+	int i, nents, queued, len, cache_len, extra, n_cdesc = 0, ret = 0;
+
+	queued = len = req->len - req->processed;
+	if (queued < crypto_ahash_blocksize(ahash))
+		cache_len = queued;
+	else
+		cache_len = queued - areq->nbytes;
+
+	/*
+	 * If this is not the last request and the queued data does not fit
+	 * into full blocks, cache it for the next send() call.
+	 */
+	extra = queued & (crypto_ahash_blocksize(ahash) - 1);
+	if (!req->last_req && extra) {
+		sg_pcopy_to_buffer(areq->src, sg_nents(areq->src),
+				   req->cache_next, extra, areq->nbytes - extra);
+
+		queued -= extra;
+		len -= extra;
+	}
+
+	request->req = &areq->base;
+	ctx->base.handle_result = safexcel_handle_result;
+
+	spin_lock_bh(&priv->ring[ring].egress_lock);
+
+	/* Add a command descriptor for the cached data, if any */
+	if (cache_len) {
+		ctx->base.cache = kzalloc(cache_len, EIP197_GFP_FLAGS(*async));
+		if (!ctx->base.cache) {
+			ret = -ENOMEM;
+			goto unlock;
+		}
+		memcpy(ctx->base.cache, req->cache, cache_len);
+		ctx->base.cache_dma = dma_map_single(priv->dev, ctx->base.cache,
+						     cache_len, DMA_TO_DEVICE);
+		if (dma_mapping_error(priv->dev, ctx->base.cache_dma)) {
+			ret = -EINVAL;
+			goto free_cache;
+		}
+
+		ctx->base.cache_sz = cache_len;
+		first_cdesc = safexcel_add_cdesc(priv, ring, 1,
+						 (cache_len == len),
+						 ctx->base.cache_dma,
+						 cache_len, len,
+						 ctx->base.ctxr_dma);
+		if (IS_ERR(first_cdesc)) {
+			ret = PTR_ERR(first_cdesc);
+			goto unmap_cache;
+		}
+		n_cdesc++;
+
+		queued -= cache_len;
+		if (!queued)
+			goto send_command;
+	}
+
+	/* Now handle the current ahash request buffer(s) */
+	nents = dma_map_sg(priv->dev, areq->src,
+		       sg_nents_for_len(areq->src, areq->nbytes),
+		       DMA_TO_DEVICE);
+	if (!nents) {
+		ret = -ENOMEM;
+		goto cdesc_rollback;
+	}
+
+	for_each_sg(areq->src, sg, nents, i) {
+		int sglen = sg_dma_len(sg);
+
+		/* Do not overflow the request */
+		if (queued - sglen < 0)
+			sglen = queued;
+
+		cdesc = safexcel_add_cdesc(priv, ring, !n_cdesc,
+					   !(queued - sglen), sg_dma_address(sg),
+					   sglen, len, ctx->base.ctxr_dma);
+		if (IS_ERR(cdesc)) {
+			ret = PTR_ERR(cdesc);
+			goto cdesc_rollback;
+		}
+		n_cdesc++;
+
+		if (n_cdesc == 1)
+			first_cdesc = cdesc;
+
+		queued -= sglen;
+		if (!queued)
+			break;
+	}
+
+send_command:
+	/* Setup the context options */
+	safexcel_context_control(ctx, req, first_cdesc, req->state_sz,
+				 crypto_ahash_blocksize(ahash));
+
+	/* Add the token */
+	safexcel_hash_token(first_cdesc, len, req->state_sz);
+
+	ctx->base.result_dma = dma_map_single(priv->dev, areq->result,
+					      req->state_sz, DMA_FROM_DEVICE);
+	if (dma_mapping_error(priv->dev, ctx->base.result_dma)) {
+		ret = -EINVAL;
+		goto cdesc_rollback;
+	}
+
+	/* Add a result descriptor */
+	rdesc = safexcel_add_rdesc(priv, ring, 1, 1, ctx->base.result_dma,
+				   req->state_sz);
+	if (IS_ERR(rdesc)) {
+		ret = PTR_ERR(rdesc);
+		goto cdesc_rollback;
+	}
+
+	req->processed += len;
+	spin_unlock_bh(&priv->ring[ring].egress_lock);
+
+	*commands = n_cdesc;
+	*results = 1;
+	return 0;
+
+cdesc_rollback:
+	for (i = 0; i < n_cdesc; i++)
+		safexcel_ring_rollback_wptr(priv, &priv->ring[ring].cdr);
+unmap_cache:
+	if (ctx->base.cache_dma) {
+		dma_unmap_single(priv->dev, ctx->base.cache_dma,
+				 ctx->base.cache_sz, DMA_TO_DEVICE);
+		ctx->base.cache_sz = 0;
+	}
+free_cache:
+	if (ctx->base.cache) {
+		kfree(ctx->base.cache);
+		ctx->base.cache = NULL;
+	}
+
+unlock:
+	spin_unlock_bh(&priv->ring[ring].egress_lock);
+	return ret;
+}
+
+static inline bool safexcel_ahash_needs_inv_get(struct ahash_request *areq)
+{
+	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(crypto_ahash_reqtfm(areq));
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
+	struct crypto_ahash *ahash = crypto_ahash_reqtfm(areq);
+	unsigned int state_w_sz = req->state_sz / sizeof(u32);
+	int i;
+
+	for (i = 0; i < state_w_sz; i++)
+		if (ctx->base.ctxr->data[i] != cpu_to_le32(req->state[i]))
+			return true;
+
+	if (ctx->base.ctxr->data[state_w_sz] !=
+	    cpu_to_le32(req->processed / crypto_ahash_blocksize(ahash)))
+		return true;
+
+	return false;
+}
+
+static int safexcel_handle_inv_result(struct safexcel_crypto_priv *priv,
+				      int ring,
+				      struct crypto_async_request *async,
+				      bool *should_complete, int *ret)
+{
+	struct safexcel_result_desc *rdesc;
+	struct ahash_request *areq = ahash_request_cast(async);
+	struct crypto_ahash *ahash = crypto_ahash_reqtfm(areq);
+	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(ahash);
+	int enq_ret;
+
+	*ret = 0;
+
+	spin_lock_bh(&priv->ring[ring].egress_lock);
+	rdesc = safexcel_ring_next_rptr(priv, &priv->ring[ring].rdr);
+	if (IS_ERR(rdesc)) {
+		dev_err(priv->dev,
+			"hash: invalidate: could not retrieve the result descriptor\n");
+		*ret = PTR_ERR(rdesc);
+	} else if (rdesc->result_data.error_code) {
+		dev_err(priv->dev,
+			"hash: invalidate: result descriptor error (%d)\n",
+			rdesc->result_data.error_code);
+		*ret = -EINVAL;
+	}
+
+	safexcel_complete(priv, ring);
+	spin_unlock_bh(&priv->ring[ring].egress_lock);
+
+	if (ctx->base.exit_inv) {
+		dma_pool_free(priv->context_pool, ctx->base.ctxr,
+			      ctx->base.ctxr_dma);
+
+		*should_complete = true;
+		return 1;
+	}
+
+	ctx->base.ring = safexcel_select_ring(priv);
+	ctx->base.needs_inv = false;
+	ctx->base.send = safexcel_ahash_send;
+
+	spin_lock_bh(&priv->lock);
+	enq_ret = crypto_enqueue_request(&priv->queue, async);
+	spin_unlock_bh(&priv->lock);
+
+	if (enq_ret != -EINPROGRESS)
+		*ret = enq_ret;
+
+	priv->need_dequeue = true;
+	*should_complete = false;
+
+	return 1;
+}
+
+static int safexcel_ahash_send_inv(struct crypto_async_request *async,
+				   int ring, struct safexcel_request *request,
+				   int *commands, int *results)
+{
+	struct ahash_request *areq = ahash_request_cast(async);
+	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(crypto_ahash_reqtfm(areq));
+	int ret;
+
+	ctx->base.handle_result = safexcel_handle_inv_result;
+	ret = safexcel_invalidate_cache(async, &ctx->base, ctx->priv,
+					ctx->base.ctxr_dma, ring, request);
+	if (unlikely(ret))
+		return ret;
+
+	*commands = 1;
+	*results = 1;
+
+	return 0;
+}
+
+static int safexcel_ahash_exit_inv(struct crypto_tfm *tfm)
+{
+	struct safexcel_ahash_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct safexcel_crypto_priv *priv = ctx->priv;
+	struct ahash_request req;
+	struct safexcel_inv_result result = { 0 };
+
+	memset(&req, 0, sizeof(struct ahash_request));
+
+	/* create invalidation request */
+	init_completion(&result.completion);
+	ahash_request_set_callback(&req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+				   safexcel_inv_complete, &result);
+
+	ahash_request_set_tfm(&req, __crypto_ahash_cast(tfm));
+	ctx = crypto_tfm_ctx(req.base.tfm);
+	ctx->base.exit_inv = true;
+	ctx->base.send = safexcel_ahash_send_inv;
+
+	spin_lock_bh(&priv->lock);
+	crypto_enqueue_request(&priv->queue, &req.base);
+	spin_unlock_bh(&priv->lock);
+
+	if (!priv->need_dequeue)
+		safexcel_dequeue(priv);
+
+	wait_for_completion_interruptible(&result.completion);
+
+	if (result.error) {
+		dev_warn(priv->dev, "hash: completion error (%d)\n",
+			 result.error);
+		return result.error;
+	}
+
+	return 0;
+}
+
+static int safexcel_ahash_cache(struct ahash_request *areq)
+{
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
+	struct crypto_ahash *ahash = crypto_ahash_reqtfm(areq);
+	int queued, cache_len;
+
+	cache_len = req->len - areq->nbytes - req->processed;
+	queued = req->len - req->processed;
+
+	/*
+	 * In case there isn't enough bytes to proceed (less than a
+	 * block size), cache the data until we have enough.
+	 */
+	if (cache_len + areq->nbytes <= crypto_ahash_blocksize(ahash)) {
+		sg_pcopy_to_buffer(areq->src, sg_nents(areq->src),
+				   req->cache + cache_len,
+				   areq->nbytes, 0);
+		return areq->nbytes;
+	}
+
+	/* We could'nt cache all the data */
+	return -E2BIG;
+}
+
+static int safexcel_ahash_enqueue(struct ahash_request *areq)
+{
+	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(crypto_ahash_reqtfm(areq));
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
+	struct safexcel_crypto_priv *priv = ctx->priv;
+	int ret;
+
+	ctx->base.send = safexcel_ahash_send;
+
+	if (req->processed && ctx->digest == CONTEXT_CONTROL_DIGEST_PRECOMPUTED)
+		ctx->base.needs_inv = safexcel_ahash_needs_inv_get(areq);
+
+	if (ctx->base.ctxr) {
+		if (ctx->base.needs_inv)
+			ctx->base.send = safexcel_ahash_send_inv;
+	} else {
+		ctx->base.ring = safexcel_select_ring(priv);
+		ctx->base.ctxr = dma_pool_zalloc(priv->context_pool,
+						 EIP197_GFP_FLAGS(areq->base),
+						 &ctx->base.ctxr_dma);
+		if (!ctx->base.ctxr)
+			return -ENOMEM;
+	}
+
+	spin_lock_bh(&priv->lock);
+	ret = crypto_enqueue_request(&priv->queue, &areq->base);
+	spin_unlock_bh(&priv->lock);
+
+	if (!priv->need_dequeue)
+		safexcel_dequeue(priv);
+
+	return ret;
+}
+
+static int safexcel_ahash_update(struct ahash_request *areq)
+{
+	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(crypto_ahash_reqtfm(areq));
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
+	struct crypto_ahash *ahash = crypto_ahash_reqtfm(areq);
+
+	/* If the request is 0 length, do nothing */
+	if (!areq->nbytes)
+		return 0;
+
+	req->len += areq->nbytes;
+
+	safexcel_ahash_cache(areq);
+
+	/*
+	 * We're not doing partial updates when performing an hmac request.
+	 * Everything will be handled by the final() call.
+	 */
+	if (ctx->digest == CONTEXT_CONTROL_DIGEST_HMAC)
+		return 0;
+
+	if (req->hmac)
+		return safexcel_ahash_enqueue(areq);
+
+	if (!req->last_req &&
+	    req->len - req->processed > crypto_ahash_blocksize(ahash))
+		return safexcel_ahash_enqueue(areq);
+
+	return 0;
+}
+
+static int safexcel_ahash_final(struct ahash_request *areq)
+{
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
+	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(crypto_ahash_reqtfm(areq));
+
+	req->last_req = true;
+	req->finish = true;
+
+	/* If we have an overall 0 length request */
+	if (!(req->len + areq->nbytes)) {
+		if (ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA1)
+			memcpy(areq->result, sha1_zero_message_hash,
+			       SHA1_DIGEST_SIZE);
+		else if (ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA224)
+			memcpy(areq->result, sha224_zero_message_hash,
+			       SHA224_DIGEST_SIZE);
+		else if (ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA256)
+			memcpy(areq->result, sha256_zero_message_hash,
+			       SHA256_DIGEST_SIZE);
+
+		return 0;
+	}
+
+	return safexcel_ahash_enqueue(areq);
+}
+
+static int safexcel_ahash_finup(struct ahash_request *areq)
+{
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
+
+	req->last_req = true;
+	req->finish = true;
+
+	safexcel_ahash_update(areq);
+	return safexcel_ahash_final(areq);
+}
+
+static int safexcel_ahash_export(struct ahash_request *areq, void *out)
+{
+	struct crypto_ahash *ahash = crypto_ahash_reqtfm(areq);
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
+	struct safexcel_ahash_export_state *export = out;
+
+	export->len = req->len;
+	export->processed = req->processed;
+
+	memcpy(export->state, req->state, req->state_sz);
+	memset(export->cache, 0, crypto_ahash_blocksize(ahash));
+	memcpy(export->cache, req->cache, crypto_ahash_blocksize(ahash));
+
+	return 0;
+}
+
+static int safexcel_ahash_import(struct ahash_request *areq, const void *in)
+{
+	struct crypto_ahash *ahash = crypto_ahash_reqtfm(areq);
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
+	const struct safexcel_ahash_export_state *export = in;
+	int ret;
+
+	ret = crypto_ahash_init(areq);
+	if (ret)
+		return ret;
+
+	req->len = export->len;
+	req->processed = export->processed;
+
+	memcpy(req->cache, export->cache, crypto_ahash_blocksize(ahash));
+	memcpy(req->state, export->state, req->state_sz);
+
+	return 0;
+}
+
+static int safexcel_ahash_cra_init(struct crypto_tfm *tfm)
+{
+	struct safexcel_ahash_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct safexcel_alg_template *tmpl =
+		container_of(__crypto_ahash_alg(tfm->__crt_alg),
+			     struct safexcel_alg_template, alg.ahash);
+
+	ctx->priv = tmpl->priv;
+
+	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
+				 sizeof(struct safexcel_ahash_req));
+	return 0;
+}
+
+static int safexcel_sha1_init(struct ahash_request *areq)
+{
+	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(crypto_ahash_reqtfm(areq));
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
+
+	memset(req, 0, sizeof(*req));
+
+	req->state[0] = SHA1_H0;
+	req->state[1] = SHA1_H1;
+	req->state[2] = SHA1_H2;
+	req->state[3] = SHA1_H3;
+	req->state[4] = SHA1_H4;
+
+	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA1;
+	ctx->digest = CONTEXT_CONTROL_DIGEST_PRECOMPUTED;
+	req->state_sz = SHA1_DIGEST_SIZE;
+
+	return 0;
+}
+
+static int safexcel_sha1_digest(struct ahash_request *areq)
+{
+	int ret = safexcel_sha1_init(areq);
+
+	if (ret)
+		return ret;
+
+	return safexcel_ahash_finup(areq);
+}
+
+static void safexcel_ahash_cra_exit(struct crypto_tfm *tfm)
+{
+	struct safexcel_ahash_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct safexcel_crypto_priv *priv = ctx->priv;
+	int ret;
+
+	/* context not allocated, skip invalidation */
+	if (!ctx->base.ctxr)
+		return;
+
+	ret = safexcel_ahash_exit_inv(tfm);
+	if (ret)
+		dev_warn(priv->dev, "hash: invalidation error %d\n", ret);
+}
+
+struct safexcel_alg_template safexcel_alg_sha1 = {
+	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.alg.ahash = {
+		.init = safexcel_sha1_init,
+		.update = safexcel_ahash_update,
+		.final = safexcel_ahash_final,
+		.finup = safexcel_ahash_finup,
+		.digest = safexcel_sha1_digest,
+		.export = safexcel_ahash_export,
+		.import = safexcel_ahash_import,
+		.halg = {
+			.digestsize = SHA1_DIGEST_SIZE,
+			.statesize = sizeof(struct safexcel_ahash_export_state),
+			.base = {
+				.cra_name = "sha1",
+				.cra_driver_name = "safexcel-sha1",
+				.cra_priority = 300,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_KERN_DRIVER_ONLY,
+				.cra_blocksize = SHA1_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct safexcel_ahash_ctx),
+				.cra_init = safexcel_ahash_cra_init,
+				.cra_exit = safexcel_ahash_cra_exit,
+				.cra_module = THIS_MODULE,
+			},
+		},
+	},
+};
+
+static int safexcel_hmac_sha1_init(struct ahash_request *areq)
+{
+	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(crypto_ahash_reqtfm(areq));
+
+	safexcel_sha1_init(areq);
+	ctx->digest = CONTEXT_CONTROL_DIGEST_HMAC;
+	return 0;
+}
+
+static int safexcel_hmac_sha1_digest(struct ahash_request *areq)
+{
+	int ret = safexcel_hmac_sha1_init(areq);
+
+	if (ret)
+		return ret;
+
+	return safexcel_ahash_finup(areq);
+}
+
+struct safexcel_ahash_result {
+	struct completion completion;
+	int error;
+};
+
+static void safexcel_ahash_complete(struct crypto_async_request *req, int error)
+{
+	struct safexcel_ahash_result *result = req->data;
+
+	if (error == -EINPROGRESS)
+		return;
+
+	result->error = error;
+	complete(&result->completion);
+}
+
+static int safexcel_hmac_init_pad(struct ahash_request *areq,
+				  unsigned int blocksize, const u8 *key,
+				  unsigned int keylen, u8 *ipad, u8 *opad)
+{
+	struct safexcel_ahash_result result;
+	struct scatterlist sg;
+	int ret, i;
+	u8 *keydup;
+
+	if (keylen <= blocksize) {
+		memcpy(ipad, key, keylen);
+	} else {
+		keydup = kmemdup(key, keylen, GFP_KERNEL);
+		if (!keydup)
+			return -ENOMEM;
+
+		ahash_request_set_callback(areq, CRYPTO_TFM_REQ_MAY_BACKLOG,
+					   safexcel_ahash_complete, &result);
+		sg_init_one(&sg, keydup, keylen);
+		ahash_request_set_crypt(areq, &sg, ipad, keylen);
+		init_completion(&result.completion);
+
+		ret = crypto_ahash_digest(areq);
+		if (ret == -EINPROGRESS) {
+			wait_for_completion_interruptible(&result.completion);
+			ret = result.error;
+		}
+
+		/* Avoid leaking */
+		memzero_explicit(keydup, keylen);
+		kfree(keydup);
+
+		if (ret)
+			return ret;
+
+		keylen = crypto_ahash_digestsize(crypto_ahash_reqtfm(areq));
+	}
+
+	memset(ipad + keylen, 0, blocksize - keylen);
+	memcpy(opad, ipad, blocksize);
+
+	for (i = 0; i < blocksize; i++) {
+		ipad[i] ^= 0x36;
+		opad[i] ^= 0x5c;
+	}
+
+	return 0;
+}
+
+static int safexcel_hmac_init_iv(struct ahash_request *areq,
+				 unsigned int blocksize, u8 *pad, void *state)
+{
+	struct safexcel_ahash_result result;
+	struct safexcel_ahash_req *req;
+	struct scatterlist sg;
+	int ret;
+
+	ahash_request_set_callback(areq, CRYPTO_TFM_REQ_MAY_BACKLOG,
+				   safexcel_ahash_complete, &result);
+	sg_init_one(&sg, pad, blocksize);
+	ahash_request_set_crypt(areq, &sg, pad, blocksize);
+	init_completion(&result.completion);
+
+	ret = crypto_ahash_init(areq);
+	if (ret)
+		return ret;
+
+	req = ahash_request_ctx(areq);
+	req->hmac = true;
+	req->last_req = true;
+
+	ret = crypto_ahash_update(areq);
+	if (ret && ret != -EINPROGRESS)
+		return ret;
+
+	wait_for_completion_interruptible(&result.completion);
+	if (result.error)
+		return result.error;
+
+	return crypto_ahash_export(areq, state);
+}
+
+static int safexcel_hmac_setkey(const char *alg, const u8 *key,
+				unsigned int keylen, void *istate, void *ostate)
+{
+	struct ahash_request *areq;
+	struct crypto_ahash *tfm;
+	unsigned int blocksize;
+	u8 *ipad, *opad;
+	int ret;
+
+	tfm = crypto_alloc_ahash(alg, CRYPTO_ALG_TYPE_AHASH,
+				 CRYPTO_ALG_TYPE_AHASH_MASK);
+	if (IS_ERR(tfm))
+		return PTR_ERR(tfm);
+
+	areq = ahash_request_alloc(tfm, GFP_KERNEL);
+	if (!areq) {
+		ret = -ENOMEM;
+		goto free_ahash;
+	}
+
+	crypto_ahash_clear_flags(tfm, ~0);
+	blocksize = crypto_tfm_alg_blocksize(crypto_ahash_tfm(tfm));
+
+	ipad = kzalloc(2 * blocksize, GFP_KERNEL);
+	if (!ipad) {
+		ret = -ENOMEM;
+		goto free_request;
+	}
+
+	opad = ipad + blocksize;
+
+	ret = safexcel_hmac_init_pad(areq, blocksize, key, keylen, ipad, opad);
+	if (ret)
+		goto free_ipad;
+
+	ret = safexcel_hmac_init_iv(areq, blocksize, ipad, istate);
+	if (ret)
+		goto free_ipad;
+
+	ret = safexcel_hmac_init_iv(areq, blocksize, opad, ostate);
+
+free_ipad:
+	kfree(ipad);
+free_request:
+	ahash_request_free(areq);
+free_ahash:
+	crypto_free_ahash(tfm);
+
+	return ret;
+}
+
+static int safexcel_hmac_sha1_setkey(struct crypto_ahash *tfm, const u8 *key,
+				     unsigned int keylen)
+{
+	struct safexcel_ahash_ctx *ctx = crypto_tfm_ctx(crypto_ahash_tfm(tfm));
+	struct safexcel_ahash_export_state istate, ostate;
+	int ret, i;
+
+	ret = safexcel_hmac_setkey("safexcel-sha1", key, keylen, &istate, &ostate);
+	if (ret)
+		return ret;
+
+	memcpy(ctx->ipad, &istate.state, SHA1_DIGEST_SIZE);
+	memcpy(ctx->opad, &ostate.state, SHA1_DIGEST_SIZE);
+
+	for (i = 0; i < ARRAY_SIZE(istate.state); i++) {
+		if (ctx->ipad[i] != le32_to_cpu(istate.state[i]) ||
+		    ctx->opad[i] != le32_to_cpu(ostate.state[i])) {
+			ctx->base.needs_inv = true;
+			break;
+		}
+	}
+
+	return 0;
+}
+
+struct safexcel_alg_template safexcel_alg_hmac_sha1 = {
+	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.alg.ahash = {
+		.init = safexcel_hmac_sha1_init,
+		.update = safexcel_ahash_update,
+		.final = safexcel_ahash_final,
+		.finup = safexcel_ahash_finup,
+		.digest = safexcel_hmac_sha1_digest,
+		.setkey = safexcel_hmac_sha1_setkey,
+		.export = safexcel_ahash_export,
+		.import = safexcel_ahash_import,
+		.halg = {
+			.digestsize = SHA1_DIGEST_SIZE,
+			.statesize = sizeof(struct safexcel_ahash_export_state),
+			.base = {
+				.cra_name = "hmac(sha1)",
+				.cra_driver_name = "safexcel-hmac-sha1",
+				.cra_priority = 300,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_KERN_DRIVER_ONLY,
+				.cra_blocksize = SHA1_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct safexcel_ahash_ctx),
+				.cra_init = safexcel_ahash_cra_init,
+				.cra_exit = safexcel_ahash_cra_exit,
+				.cra_module = THIS_MODULE,
+			},
+		},
+	},
+};
+
+static int safexcel_sha256_init(struct ahash_request *areq)
+{
+	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(crypto_ahash_reqtfm(areq));
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
+
+	memset(req, 0, sizeof(*req));
+
+	req->state[0] = SHA256_H0;
+	req->state[1] = SHA256_H1;
+	req->state[2] = SHA256_H2;
+	req->state[3] = SHA256_H3;
+	req->state[4] = SHA256_H4;
+	req->state[5] = SHA256_H5;
+	req->state[6] = SHA256_H6;
+	req->state[7] = SHA256_H7;
+
+	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA256;
+	ctx->digest = CONTEXT_CONTROL_DIGEST_PRECOMPUTED;
+	req->state_sz = SHA256_DIGEST_SIZE;
+
+	return 0;
+}
+
+static int safexcel_sha256_digest(struct ahash_request *areq)
+{
+	int ret = safexcel_sha256_init(areq);
+
+	if (ret)
+		return ret;
+
+	return safexcel_ahash_finup(areq);
+}
+
+struct safexcel_alg_template safexcel_alg_sha256 = {
+	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.alg.ahash = {
+		.init = safexcel_sha256_init,
+		.update = safexcel_ahash_update,
+		.final = safexcel_ahash_final,
+		.finup = safexcel_ahash_finup,
+		.digest = safexcel_sha256_digest,
+		.export = safexcel_ahash_export,
+		.import = safexcel_ahash_import,
+		.halg = {
+			.digestsize = SHA256_DIGEST_SIZE,
+			.statesize = sizeof(struct safexcel_ahash_export_state),
+			.base = {
+				.cra_name = "sha256",
+				.cra_driver_name = "safexcel-sha256",
+				.cra_priority = 300,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_KERN_DRIVER_ONLY,
+				.cra_blocksize = SHA256_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct safexcel_ahash_ctx),
+				.cra_init = safexcel_ahash_cra_init,
+				.cra_exit = safexcel_ahash_cra_exit,
+				.cra_module = THIS_MODULE,
+			},
+		},
+	},
+};
+
+static int safexcel_sha224_init(struct ahash_request *areq)
+{
+	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(crypto_ahash_reqtfm(areq));
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
+
+	memset(req, 0, sizeof(*req));
+
+	req->state[0] = SHA224_H0;
+	req->state[1] = SHA224_H1;
+	req->state[2] = SHA224_H2;
+	req->state[3] = SHA224_H3;
+	req->state[4] = SHA224_H4;
+	req->state[5] = SHA224_H5;
+	req->state[6] = SHA224_H6;
+	req->state[7] = SHA224_H7;
+
+	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA224;
+	ctx->digest = CONTEXT_CONTROL_DIGEST_PRECOMPUTED;
+	req->state_sz = SHA256_DIGEST_SIZE;
+
+	return 0;
+}
+
+static int safexcel_sha224_digest(struct ahash_request *areq)
+{
+	int ret = safexcel_sha224_init(areq);
+
+	if (ret)
+		return ret;
+
+	return safexcel_ahash_finup(areq);
+}
+
+struct safexcel_alg_template safexcel_alg_sha224 = {
+	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.alg.ahash = {
+		.init = safexcel_sha224_init,
+		.update = safexcel_ahash_update,
+		.final = safexcel_ahash_final,
+		.finup = safexcel_ahash_finup,
+		.digest = safexcel_sha224_digest,
+		.export = safexcel_ahash_export,
+		.import = safexcel_ahash_import,
+		.halg = {
+			.digestsize = SHA224_DIGEST_SIZE,
+			.statesize = sizeof(struct safexcel_ahash_export_state),
+			.base = {
+				.cra_name = "sha224",
+				.cra_driver_name = "safexcel-sha224",
+				.cra_priority = 300,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_KERN_DRIVER_ONLY,
+				.cra_blocksize = SHA224_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct safexcel_ahash_ctx),
+				.cra_init = safexcel_ahash_cra_init,
+				.cra_exit = safexcel_ahash_cra_exit,
+				.cra_module = THIS_MODULE,
+			},
+		},
+	},
+};

drivers/crypto/inside-secure/safexcel_ring.c

+/*
+ * Copyright (C) 2017 Marvell
+ *
+ * Antoine Tenart <antoine.tenart@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/dma-mapping.h>
+#include <linux/spinlock.h>
+
+#include "safexcel.h"
+
+int safexcel_init_ring_descriptors(struct safexcel_crypto_priv *priv,
+				   struct safexcel_ring *cdr,
+				   struct safexcel_ring *rdr)
+{
+	cdr->offset = sizeof(u32) * priv->config.cd_offset;
+	cdr->base = dmam_alloc_coherent(priv->dev,
+					cdr->offset * EIP197_DEFAULT_RING_SIZE,
+					&cdr->base_dma, GFP_KERNEL);
+	if (!cdr->base)
+		return -ENOMEM;
+	cdr->write = cdr->base;
+	cdr->base_end = cdr->base + cdr->offset * EIP197_DEFAULT_RING_SIZE;
+	cdr->read = cdr->base;
+
+	rdr->offset = sizeof(u32) * priv->config.rd_offset;
+	rdr->base = dmam_alloc_coherent(priv->dev,
+					rdr->offset * EIP197_DEFAULT_RING_SIZE,
+					&rdr->base_dma, GFP_KERNEL);
+	if (!rdr->base)
+		return -ENOMEM;
+	rdr->write = rdr->base;
+	rdr->base_end = rdr->base + rdr->offset * EIP197_DEFAULT_RING_SIZE;
+	rdr->read = rdr->base;
+
+	return 0;
+}
+
+inline int safexcel_select_ring(struct safexcel_crypto_priv *priv)
+{
+	return (atomic_inc_return(&priv->ring_used) % priv->config.rings);
+}
+
+static void *safexcel_ring_next_wptr(struct safexcel_crypto_priv *priv,
+				     struct safexcel_ring *ring)
+{
+	void *ptr = ring->write;
+
+	if (ring->nr == EIP197_DEFAULT_RING_SIZE - 1)
+		return ERR_PTR(-ENOMEM);
+
+	ring->write += ring->offset;
+	if (ring->write == ring->base_end)
+		ring->write = ring->base;
+
+	ring->nr++;
+	return ptr;
+}
+
+void *safexcel_ring_next_rptr(struct safexcel_crypto_priv *priv,
+			      struct safexcel_ring *ring)
+{
+	void *ptr = ring->read;
+
+	if (!ring->nr)
+		return ERR_PTR(-ENOENT);
+
+	ring->read += ring->offset;
+	if (ring->read == ring->base_end)
+		ring->read = ring->base;
+
+	ring->nr--;
+	return ptr;
+}
+
+void safexcel_ring_rollback_wptr(struct safexcel_crypto_priv *priv,
+				 struct safexcel_ring *ring)
+{
+	if (!ring->nr)
+		return;
+
+	if (ring->write == ring->base)
+		ring->write += (EIP197_DEFAULT_RING_SIZE - 1) * ring->offset;
+	else
+		ring->write -= ring->offset;
+
+	ring->nr--;
+}
+
+struct safexcel_command_desc *safexcel_add_cdesc(struct safexcel_crypto_priv *priv,
+						 int ring_id,
+						 bool first, bool last,
+						 dma_addr_t data, u32 data_len,
+						 u32 full_data_len,
+						 dma_addr_t context) {
+	struct safexcel_command_desc *cdesc;
+	int i;
+
+	cdesc = safexcel_ring_next_wptr(priv, &priv->ring[ring_id].cdr);
+	if (IS_ERR(cdesc))
+		return cdesc;
+
+	memset(cdesc, 0, sizeof(struct safexcel_command_desc));
+
+	cdesc->first_seg = first;
+	cdesc->last_seg = last;
+	cdesc->particle_size = data_len;
+	cdesc->data_lo = lower_32_bits(data);
+	cdesc->data_hi = upper_32_bits(data);
+
+	if (first && context) {
+		struct safexcel_token *token =
+			(struct safexcel_token *)cdesc->control_data.token;
+
+		cdesc->control_data.packet_length = full_data_len;
+		cdesc->control_data.options = EIP197_OPTION_MAGIC_VALUE |
+					      EIP197_OPTION_64BIT_CTX |
+					      EIP197_OPTION_CTX_CTRL_IN_CMD;
+		cdesc->control_data.context_lo =
+			(lower_32_bits(context) & GENMASK(31, 2)) >> 2;
+		cdesc->control_data.context_hi = upper_32_bits(context);
+
+		/* TODO: large xform HMAC with SHA-384/512 uses refresh = 3 */
+		cdesc->control_data.refresh = 2;
+
+		for (i = 0; i < EIP197_MAX_TOKENS; i++)
+			eip197_noop_token(&token[i]);
+	}
+
+	return cdesc;
+}
+
+struct safexcel_result_desc *safexcel_add_rdesc(struct safexcel_crypto_priv *priv,
+						int ring_id,
+						bool first, bool last,
+						dma_addr_t data, u32 len)
+{
+	struct safexcel_result_desc *rdesc;
+
+	rdesc = safexcel_ring_next_wptr(priv, &priv->ring[ring_id].rdr);
+	if (IS_ERR(rdesc))
+		return rdesc;
+
+	memset(rdesc, 0, sizeof(struct safexcel_result_desc));
+
+	rdesc->first_seg = first;
+	rdesc->last_seg = last;
+	rdesc->particle_size = len;
+	rdesc->data_lo = lower_32_bits(data);
+	rdesc->data_hi = upper_32_bits(data);
+
+	return rdesc;
+}